xpressengine /
xe-core
@@ -124,6 +124,9 @@ discard block |
||
| 124 | 124 | const CHARACTR = 4; |
| 125 | 125 | const EOF = 5; |
| 126 | 126 | |
| 127 | + /** |
|
| 128 | + * @param string $data |
|
| 129 | + */ |
|
| 127 | 130 | public function __construct($data) { |
| 128 | 131 | |
| 129 | 132 | $this->data = $data; |
@@ -143,12 +146,20 @@ discard block |
||
| 143 | 146 | return $this->tree->save(); |
| 144 | 147 | } |
| 145 | 148 | |
| 149 | + /** |
|
| 150 | + * @return string |
|
| 151 | + */ |
|
| 146 | 152 | private function char() { |
| 147 | 153 | return ($this->char < $this->EOF) |
| 148 | 154 | ? $this->data[$this->char] |
| 149 | 155 | : false; |
| 150 | 156 | } |
| 151 | 157 | |
| 158 | + /** |
|
| 159 | + * @param integer $s |
|
| 160 | + * |
|
| 161 | + * @return string |
|
| 162 | + */ |
|
| 152 | 163 | private function character($s, $l = 0) { |
| 153 | 164 | if($s + $l < $this->EOF) { |
| 154 | 165 | if($l === 0) { |
@@ -159,6 +170,10 @@ discard block |
||
| 159 | 170 | } |
| 160 | 171 | } |
| 161 | 172 | |
| 173 | + /** |
|
| 174 | + * @param string $char_class |
|
| 175 | + * @param integer $start |
|
| 176 | + */ |
|
| 162 | 177 | private function characters($char_class, $start) { |
| 163 | 178 | return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start)); |
| 164 | 179 | } |
@@ -3767,6 +3782,9 @@ discard block |
||
| 3767 | 3782 | return self::PHRASING; |
| 3768 | 3783 | } |
| 3769 | 3784 | |
| 3785 | + /** |
|
| 3786 | + * @param string[] $elements |
|
| 3787 | + */ |
|
| 3770 | 3788 | private function clearStackToTableContext($elements) { |
| 3771 | 3789 | /* When the steps above require the UA to clear the stack back to a |
| 3772 | 3790 | table context, it means that the UA must, while the current node is not |
@@ -12,26 +12,26 @@ discard block |
||
| 12 | 12 | |
| 13 | 13 | class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex { |
| 14 | 14 | |
| 15 | - public function tokenizeHTML($html, $config, $context) { |
|
| 16 | - $new_html = $this->normalize($html, $config, $context); |
|
| 17 | - $new_html = $this->wrapHTML($new_html, $config, $context); |
|
| 18 | - try { |
|
| 19 | - $parser = new HTML5($new_html); |
|
| 20 | - $doc = $parser->save(); |
|
| 21 | - } catch (DOMException $e) { |
|
| 22 | - // Uh oh, it failed. Punt to DirectLex. |
|
| 23 | - $lexer = new HTMLPurifier_Lexer_DirectLex(); |
|
| 24 | - $context->register('PH5PError', $e); // save the error, so we can detect it |
|
| 25 | - return $lexer->tokenizeHTML($html, $config, $context); // use original HTML |
|
| 26 | - } |
|
| 27 | - $tokens = array(); |
|
| 28 | - $this->tokenizeDOM( |
|
| 29 | - $doc->getElementsByTagName('html')->item(0)-> // <html> |
|
| 30 | - getElementsByTagName('body')->item(0)-> // <body> |
|
| 31 | - getElementsByTagName('div')->item(0) // <div> |
|
| 32 | - , $tokens); |
|
| 33 | - return $tokens; |
|
| 34 | - } |
|
| 15 | + public function tokenizeHTML($html, $config, $context) { |
|
| 16 | + $new_html = $this->normalize($html, $config, $context); |
|
| 17 | + $new_html = $this->wrapHTML($new_html, $config, $context); |
|
| 18 | + try { |
|
| 19 | + $parser = new HTML5($new_html); |
|
| 20 | + $doc = $parser->save(); |
|
| 21 | + } catch (DOMException $e) { |
|
| 22 | + // Uh oh, it failed. Punt to DirectLex. |
|
| 23 | + $lexer = new HTMLPurifier_Lexer_DirectLex(); |
|
| 24 | + $context->register('PH5PError', $e); // save the error, so we can detect it |
|
| 25 | + return $lexer->tokenizeHTML($html, $config, $context); // use original HTML |
|
| 26 | + } |
|
| 27 | + $tokens = array(); |
|
| 28 | + $this->tokenizeDOM( |
|
| 29 | + $doc->getElementsByTagName('html')->item(0)-> // <html> |
|
| 30 | + getElementsByTagName('body')->item(0)-> // <body> |
|
| 31 | + getElementsByTagName('div')->item(0) // <div> |
|
| 32 | + , $tokens); |
|
| 33 | + return $tokens; |
|
| 34 | + } |
|
| 35 | 35 | |
| 36 | 36 | } |
| 37 | 37 | |
@@ -61,145 +61,145 @@ discard block |
||
| 61 | 61 | */ |
| 62 | 62 | |
| 63 | 63 | class HTML5 { |
| 64 | - private $data; |
|
| 65 | - private $char; |
|
| 66 | - private $EOF; |
|
| 67 | - private $state; |
|
| 68 | - private $tree; |
|
| 69 | - private $token; |
|
| 70 | - private $content_model; |
|
| 71 | - private $escape = false; |
|
| 72 | - private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute', |
|
| 73 | - 'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;', |
|
| 74 | - 'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;', |
|
| 75 | - 'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;', |
|
| 76 | - 'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;', |
|
| 77 | - 'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;', |
|
| 78 | - 'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;', |
|
| 79 | - 'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;', |
|
| 80 | - 'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;', |
|
| 81 | - 'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN', |
|
| 82 | - 'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;', |
|
| 83 | - 'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;', |
|
| 84 | - 'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig', |
|
| 85 | - 'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;', |
|
| 86 | - 'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;', |
|
| 87 | - 'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil', |
|
| 88 | - 'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;', |
|
| 89 | - 'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;', |
|
| 90 | - 'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;', |
|
| 91 | - 'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth', |
|
| 92 | - 'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12', |
|
| 93 | - 'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt', |
|
| 94 | - 'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc', |
|
| 95 | - 'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;', |
|
| 96 | - 'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;', |
|
| 97 | - 'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;', |
|
| 98 | - 'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro', |
|
| 99 | - 'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;', |
|
| 100 | - 'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;', |
|
| 101 | - 'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;', |
|
| 102 | - 'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash', |
|
| 103 | - 'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;', |
|
| 104 | - 'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;', |
|
| 105 | - 'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;', |
|
| 106 | - 'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;', |
|
| 107 | - 'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;', |
|
| 108 | - 'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;', |
|
| 109 | - 'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;', |
|
| 110 | - 'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;', |
|
| 111 | - 'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc', |
|
| 112 | - 'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;', |
|
| 113 | - 'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;'); |
|
| 114 | - |
|
| 115 | - const PCDATA = 0; |
|
| 116 | - const RCDATA = 1; |
|
| 117 | - const CDATA = 2; |
|
| 118 | - const PLAINTEXT = 3; |
|
| 119 | - |
|
| 120 | - const DOCTYPE = 0; |
|
| 121 | - const STARTTAG = 1; |
|
| 122 | - const ENDTAG = 2; |
|
| 123 | - const COMMENT = 3; |
|
| 124 | - const CHARACTR = 4; |
|
| 125 | - const EOF = 5; |
|
| 126 | - |
|
| 127 | - public function __construct($data) { |
|
| 128 | - |
|
| 129 | - $this->data = $data; |
|
| 130 | - $this->char = -1; |
|
| 131 | - $this->EOF = strlen($data); |
|
| 132 | - $this->tree = new HTML5TreeConstructer; |
|
| 133 | - $this->content_model = self::PCDATA; |
|
| 134 | - |
|
| 135 | - $this->state = 'data'; |
|
| 136 | - |
|
| 137 | - while($this->state !== null) { |
|
| 138 | - $this->{$this->state.'State'}(); |
|
| 139 | - } |
|
| 140 | - } |
|
| 141 | - |
|
| 142 | - public function save() { |
|
| 143 | - return $this->tree->save(); |
|
| 144 | - } |
|
| 145 | - |
|
| 146 | - private function char() { |
|
| 147 | - return ($this->char < $this->EOF) |
|
| 148 | - ? $this->data[$this->char] |
|
| 149 | - : false; |
|
| 150 | - } |
|
| 151 | - |
|
| 152 | - private function character($s, $l = 0) { |
|
| 153 | - if($s + $l < $this->EOF) { |
|
| 154 | - if($l === 0) { |
|
| 155 | - return $this->data[$s]; |
|
| 156 | - } else { |
|
| 157 | - return substr($this->data, $s, $l); |
|
| 158 | - } |
|
| 159 | - } |
|
| 160 | - } |
|
| 161 | - |
|
| 162 | - private function characters($char_class, $start) { |
|
| 163 | - return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start)); |
|
| 164 | - } |
|
| 165 | - |
|
| 166 | - private function dataState() { |
|
| 167 | - // Consume the next input character |
|
| 168 | - $this->char++; |
|
| 169 | - $char = $this->char(); |
|
| 170 | - |
|
| 171 | - if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { |
|
| 172 | - /* U+0026 AMPERSAND (&) |
|
| 64 | + private $data; |
|
| 65 | + private $char; |
|
| 66 | + private $EOF; |
|
| 67 | + private $state; |
|
| 68 | + private $tree; |
|
| 69 | + private $token; |
|
| 70 | + private $content_model; |
|
| 71 | + private $escape = false; |
|
| 72 | + private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute', |
|
| 73 | + 'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;', |
|
| 74 | + 'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;', |
|
| 75 | + 'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;', |
|
| 76 | + 'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;', |
|
| 77 | + 'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;', |
|
| 78 | + 'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;', |
|
| 79 | + 'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;', |
|
| 80 | + 'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;', |
|
| 81 | + 'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN', |
|
| 82 | + 'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;', |
|
| 83 | + 'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;', |
|
| 84 | + 'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig', |
|
| 85 | + 'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;', |
|
| 86 | + 'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;', |
|
| 87 | + 'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil', |
|
| 88 | + 'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;', |
|
| 89 | + 'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;', |
|
| 90 | + 'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;', |
|
| 91 | + 'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth', |
|
| 92 | + 'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12', |
|
| 93 | + 'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt', |
|
| 94 | + 'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc', |
|
| 95 | + 'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;', |
|
| 96 | + 'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;', |
|
| 97 | + 'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;', |
|
| 98 | + 'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro', |
|
| 99 | + 'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;', |
|
| 100 | + 'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;', |
|
| 101 | + 'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;', |
|
| 102 | + 'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash', |
|
| 103 | + 'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;', |
|
| 104 | + 'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;', |
|
| 105 | + 'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;', |
|
| 106 | + 'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;', |
|
| 107 | + 'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;', |
|
| 108 | + 'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;', |
|
| 109 | + 'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;', |
|
| 110 | + 'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;', |
|
| 111 | + 'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc', |
|
| 112 | + 'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;', |
|
| 113 | + 'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;'); |
|
| 114 | + |
|
| 115 | + const PCDATA = 0; |
|
| 116 | + const RCDATA = 1; |
|
| 117 | + const CDATA = 2; |
|
| 118 | + const PLAINTEXT = 3; |
|
| 119 | + |
|
| 120 | + const DOCTYPE = 0; |
|
| 121 | + const STARTTAG = 1; |
|
| 122 | + const ENDTAG = 2; |
|
| 123 | + const COMMENT = 3; |
|
| 124 | + const CHARACTR = 4; |
|
| 125 | + const EOF = 5; |
|
| 126 | + |
|
| 127 | + public function __construct($data) { |
|
| 128 | + |
|
| 129 | + $this->data = $data; |
|
| 130 | + $this->char = -1; |
|
| 131 | + $this->EOF = strlen($data); |
|
| 132 | + $this->tree = new HTML5TreeConstructer; |
|
| 133 | + $this->content_model = self::PCDATA; |
|
| 134 | + |
|
| 135 | + $this->state = 'data'; |
|
| 136 | + |
|
| 137 | + while($this->state !== null) { |
|
| 138 | + $this->{$this->state.'State'}(); |
|
| 139 | + } |
|
| 140 | + } |
|
| 141 | + |
|
| 142 | + public function save() { |
|
| 143 | + return $this->tree->save(); |
|
| 144 | + } |
|
| 145 | + |
|
| 146 | + private function char() { |
|
| 147 | + return ($this->char < $this->EOF) |
|
| 148 | + ? $this->data[$this->char] |
|
| 149 | + : false; |
|
| 150 | + } |
|
| 151 | + |
|
| 152 | + private function character($s, $l = 0) { |
|
| 153 | + if($s + $l < $this->EOF) { |
|
| 154 | + if($l === 0) { |
|
| 155 | + return $this->data[$s]; |
|
| 156 | + } else { |
|
| 157 | + return substr($this->data, $s, $l); |
|
| 158 | + } |
|
| 159 | + } |
|
| 160 | + } |
|
| 161 | + |
|
| 162 | + private function characters($char_class, $start) { |
|
| 163 | + return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start)); |
|
| 164 | + } |
|
| 165 | + |
|
| 166 | + private function dataState() { |
|
| 167 | + // Consume the next input character |
|
| 168 | + $this->char++; |
|
| 169 | + $char = $this->char(); |
|
| 170 | + |
|
| 171 | + if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { |
|
| 172 | + /* U+0026 AMPERSAND (&) |
|
| 173 | 173 | When the content model flag is set to one of the PCDATA or RCDATA |
| 174 | 174 | states: switch to the entity data state. Otherwise: treat it as per |
| 175 | 175 | the "anything else" entry below. */ |
| 176 | - $this->state = 'entityData'; |
|
| 176 | + $this->state = 'entityData'; |
|
| 177 | 177 | |
| 178 | - } elseif($char === '-') { |
|
| 179 | - /* If the content model flag is set to either the RCDATA state or |
|
| 178 | + } elseif($char === '-') { |
|
| 179 | + /* If the content model flag is set to either the RCDATA state or |
|
| 180 | 180 | the CDATA state, and the escape flag is false, and there are at |
| 181 | 181 | least three characters before this one in the input stream, and the |
| 182 | 182 | last four characters in the input stream, including this one, are |
| 183 | 183 | U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS, |
| 184 | 184 | and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */ |
| 185 | - if(($this->content_model === self::RCDATA || $this->content_model === |
|
| 186 | - self::CDATA) && $this->escape === false && |
|
| 187 | - $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') { |
|
| 188 | - $this->escape = true; |
|
| 189 | - } |
|
| 185 | + if(($this->content_model === self::RCDATA || $this->content_model === |
|
| 186 | + self::CDATA) && $this->escape === false && |
|
| 187 | + $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') { |
|
| 188 | + $this->escape = true; |
|
| 189 | + } |
|
| 190 | 190 | |
| 191 | - /* In any case, emit the input character as a character token. Stay |
|
| 191 | + /* In any case, emit the input character as a character token. Stay |
|
| 192 | 192 | in the data state. */ |
| 193 | - $this->emitToken(array( |
|
| 194 | - 'type' => self::CHARACTR, |
|
| 195 | - 'data' => $char |
|
| 196 | - )); |
|
| 197 | - |
|
| 198 | - /* U+003C LESS-THAN SIGN (<) */ |
|
| 199 | - } elseif($char === '<' && ($this->content_model === self::PCDATA || |
|
| 200 | - (($this->content_model === self::RCDATA || |
|
| 201 | - $this->content_model === self::CDATA) && $this->escape === false))) { |
|
| 202 | - /* When the content model flag is set to the PCDATA state: switch |
|
| 193 | + $this->emitToken(array( |
|
| 194 | + 'type' => self::CHARACTR, |
|
| 195 | + 'data' => $char |
|
| 196 | + )); |
|
| 197 | + |
|
| 198 | + /* U+003C LESS-THAN SIGN (<) */ |
|
| 199 | + } elseif($char === '<' && ($this->content_model === self::PCDATA || |
|
| 200 | + (($this->content_model === self::RCDATA || |
|
| 201 | + $this->content_model === self::CDATA) && $this->escape === false))) { |
|
| 202 | + /* When the content model flag is set to the PCDATA state: switch |
|
| 203 | 203 | to the tag open state. |
| 204 | 204 | |
| 205 | 205 | When the content model flag is set to either the RCDATA state or |
@@ -207,171 +207,171 @@ discard block |
||
| 207 | 207 | open state. |
| 208 | 208 | |
| 209 | 209 | Otherwise: treat it as per the "anything else" entry below. */ |
| 210 | - $this->state = 'tagOpen'; |
|
| 210 | + $this->state = 'tagOpen'; |
|
| 211 | 211 | |
| 212 | - /* U+003E GREATER-THAN SIGN (>) */ |
|
| 213 | - } elseif($char === '>') { |
|
| 214 | - /* If the content model flag is set to either the RCDATA state or |
|
| 212 | + /* U+003E GREATER-THAN SIGN (>) */ |
|
| 213 | + } elseif($char === '>') { |
|
| 214 | + /* If the content model flag is set to either the RCDATA state or |
|
| 215 | 215 | the CDATA state, and the escape flag is true, and the last three |
| 216 | 216 | characters in the input stream including this one are U+002D |
| 217 | 217 | HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"), |
| 218 | 218 | set the escape flag to false. */ |
| 219 | - if(($this->content_model === self::RCDATA || |
|
| 220 | - $this->content_model === self::CDATA) && $this->escape === true && |
|
| 221 | - $this->character($this->char, 3) === '-->') { |
|
| 222 | - $this->escape = false; |
|
| 223 | - } |
|
| 219 | + if(($this->content_model === self::RCDATA || |
|
| 220 | + $this->content_model === self::CDATA) && $this->escape === true && |
|
| 221 | + $this->character($this->char, 3) === '-->') { |
|
| 222 | + $this->escape = false; |
|
| 223 | + } |
|
| 224 | 224 | |
| 225 | - /* In any case, emit the input character as a character token. |
|
| 225 | + /* In any case, emit the input character as a character token. |
|
| 226 | 226 | Stay in the data state. */ |
| 227 | - $this->emitToken(array( |
|
| 228 | - 'type' => self::CHARACTR, |
|
| 229 | - 'data' => $char |
|
| 230 | - )); |
|
| 227 | + $this->emitToken(array( |
|
| 228 | + 'type' => self::CHARACTR, |
|
| 229 | + 'data' => $char |
|
| 230 | + )); |
|
| 231 | 231 | |
| 232 | - } elseif($this->char === $this->EOF) { |
|
| 233 | - /* EOF |
|
| 232 | + } elseif($this->char === $this->EOF) { |
|
| 233 | + /* EOF |
|
| 234 | 234 | Emit an end-of-file token. */ |
| 235 | - $this->EOF(); |
|
| 235 | + $this->EOF(); |
|
| 236 | 236 | |
| 237 | - } elseif($this->content_model === self::PLAINTEXT) { |
|
| 238 | - /* When the content model flag is set to the PLAINTEXT state |
|
| 237 | + } elseif($this->content_model === self::PLAINTEXT) { |
|
| 238 | + /* When the content model flag is set to the PLAINTEXT state |
|
| 239 | 239 | THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of |
| 240 | 240 | the text and emit it as a character token. */ |
| 241 | - $this->emitToken(array( |
|
| 242 | - 'type' => self::CHARACTR, |
|
| 243 | - 'data' => substr($this->data, $this->char) |
|
| 244 | - )); |
|
| 241 | + $this->emitToken(array( |
|
| 242 | + 'type' => self::CHARACTR, |
|
| 243 | + 'data' => substr($this->data, $this->char) |
|
| 244 | + )); |
|
| 245 | 245 | |
| 246 | - $this->EOF(); |
|
| 246 | + $this->EOF(); |
|
| 247 | 247 | |
| 248 | - } else { |
|
| 249 | - /* Anything else |
|
| 248 | + } else { |
|
| 249 | + /* Anything else |
|
| 250 | 250 | THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that |
| 251 | 251 | otherwise would also be treated as a character token and emit it |
| 252 | 252 | as a single character token. Stay in the data state. */ |
| 253 | - $len = strcspn($this->data, '<&', $this->char); |
|
| 254 | - $char = substr($this->data, $this->char, $len); |
|
| 255 | - $this->char += $len - 1; |
|
| 256 | - |
|
| 257 | - $this->emitToken(array( |
|
| 258 | - 'type' => self::CHARACTR, |
|
| 259 | - 'data' => $char |
|
| 260 | - )); |
|
| 261 | - |
|
| 262 | - $this->state = 'data'; |
|
| 263 | - } |
|
| 264 | - } |
|
| 265 | - |
|
| 266 | - private function entityDataState() { |
|
| 267 | - // Attempt to consume an entity. |
|
| 268 | - $entity = $this->entity(); |
|
| 269 | - |
|
| 270 | - // If nothing is returned, emit a U+0026 AMPERSAND character token. |
|
| 271 | - // Otherwise, emit the character token that was returned. |
|
| 272 | - $char = (!$entity) ? '&' : $entity; |
|
| 273 | - $this->emitToken(array( |
|
| 274 | - 'type' => self::CHARACTR, |
|
| 275 | - 'data' => $char |
|
| 276 | - )); |
|
| 277 | - |
|
| 278 | - // Finally, switch to the data state. |
|
| 279 | - $this->state = 'data'; |
|
| 280 | - } |
|
| 281 | - |
|
| 282 | - private function tagOpenState() { |
|
| 283 | - switch($this->content_model) { |
|
| 284 | - case self::RCDATA: |
|
| 285 | - case self::CDATA: |
|
| 286 | - /* If the next input character is a U+002F SOLIDUS (/) character, |
|
| 253 | + $len = strcspn($this->data, '<&', $this->char); |
|
| 254 | + $char = substr($this->data, $this->char, $len); |
|
| 255 | + $this->char += $len - 1; |
|
| 256 | + |
|
| 257 | + $this->emitToken(array( |
|
| 258 | + 'type' => self::CHARACTR, |
|
| 259 | + 'data' => $char |
|
| 260 | + )); |
|
| 261 | + |
|
| 262 | + $this->state = 'data'; |
|
| 263 | + } |
|
| 264 | + } |
|
| 265 | + |
|
| 266 | + private function entityDataState() { |
|
| 267 | + // Attempt to consume an entity. |
|
| 268 | + $entity = $this->entity(); |
|
| 269 | + |
|
| 270 | + // If nothing is returned, emit a U+0026 AMPERSAND character token. |
|
| 271 | + // Otherwise, emit the character token that was returned. |
|
| 272 | + $char = (!$entity) ? '&' : $entity; |
|
| 273 | + $this->emitToken(array( |
|
| 274 | + 'type' => self::CHARACTR, |
|
| 275 | + 'data' => $char |
|
| 276 | + )); |
|
| 277 | + |
|
| 278 | + // Finally, switch to the data state. |
|
| 279 | + $this->state = 'data'; |
|
| 280 | + } |
|
| 281 | + |
|
| 282 | + private function tagOpenState() { |
|
| 283 | + switch($this->content_model) { |
|
| 284 | + case self::RCDATA: |
|
| 285 | + case self::CDATA: |
|
| 286 | + /* If the next input character is a U+002F SOLIDUS (/) character, |
|
| 287 | 287 | consume it and switch to the close tag open state. If the next |
| 288 | 288 | input character is not a U+002F SOLIDUS (/) character, emit a |
| 289 | 289 | U+003C LESS-THAN SIGN character token and switch to the data |
| 290 | 290 | state to process the next input character. */ |
| 291 | - if($this->character($this->char + 1) === '/') { |
|
| 292 | - $this->char++; |
|
| 293 | - $this->state = 'closeTagOpen'; |
|
| 294 | - |
|
| 295 | - } else { |
|
| 296 | - $this->emitToken(array( |
|
| 297 | - 'type' => self::CHARACTR, |
|
| 298 | - 'data' => '<' |
|
| 299 | - )); |
|
| 300 | - |
|
| 301 | - $this->state = 'data'; |
|
| 302 | - } |
|
| 303 | - break; |
|
| 304 | - |
|
| 305 | - case self::PCDATA: |
|
| 306 | - // If the content model flag is set to the PCDATA state |
|
| 307 | - // Consume the next input character: |
|
| 308 | - $this->char++; |
|
| 309 | - $char = $this->char(); |
|
| 310 | - |
|
| 311 | - if($char === '!') { |
|
| 312 | - /* U+0021 EXCLAMATION MARK (!) |
|
| 291 | + if($this->character($this->char + 1) === '/') { |
|
| 292 | + $this->char++; |
|
| 293 | + $this->state = 'closeTagOpen'; |
|
| 294 | + |
|
| 295 | + } else { |
|
| 296 | + $this->emitToken(array( |
|
| 297 | + 'type' => self::CHARACTR, |
|
| 298 | + 'data' => '<' |
|
| 299 | + )); |
|
| 300 | + |
|
| 301 | + $this->state = 'data'; |
|
| 302 | + } |
|
| 303 | + break; |
|
| 304 | + |
|
| 305 | + case self::PCDATA: |
|
| 306 | + // If the content model flag is set to the PCDATA state |
|
| 307 | + // Consume the next input character: |
|
| 308 | + $this->char++; |
|
| 309 | + $char = $this->char(); |
|
| 310 | + |
|
| 311 | + if($char === '!') { |
|
| 312 | + /* U+0021 EXCLAMATION MARK (!) |
|
| 313 | 313 | Switch to the markup declaration open state. */ |
| 314 | - $this->state = 'markupDeclarationOpen'; |
|
| 314 | + $this->state = 'markupDeclarationOpen'; |
|
| 315 | 315 | |
| 316 | - } elseif($char === '/') { |
|
| 317 | - /* U+002F SOLIDUS (/) |
|
| 316 | + } elseif($char === '/') { |
|
| 317 | + /* U+002F SOLIDUS (/) |
|
| 318 | 318 | Switch to the close tag open state. */ |
| 319 | - $this->state = 'closeTagOpen'; |
|
| 319 | + $this->state = 'closeTagOpen'; |
|
| 320 | 320 | |
| 321 | - } elseif(preg_match('/^[A-Za-z]$/', $char)) { |
|
| 322 | - /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z |
|
| 321 | + } elseif(preg_match('/^[A-Za-z]$/', $char)) { |
|
| 322 | + /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z |
|
| 323 | 323 | Create a new start tag token, set its tag name to the lowercase |
| 324 | 324 | version of the input character (add 0x0020 to the character's code |
| 325 | 325 | point), then switch to the tag name state. (Don't emit the token |
| 326 | 326 | yet; further details will be filled in before it is emitted.) */ |
| 327 | - $this->token = array( |
|
| 328 | - 'name' => strtolower($char), |
|
| 329 | - 'type' => self::STARTTAG, |
|
| 330 | - 'attr' => array() |
|
| 331 | - ); |
|
| 327 | + $this->token = array( |
|
| 328 | + 'name' => strtolower($char), |
|
| 329 | + 'type' => self::STARTTAG, |
|
| 330 | + 'attr' => array() |
|
| 331 | + ); |
|
| 332 | 332 | |
| 333 | - $this->state = 'tagName'; |
|
| 333 | + $this->state = 'tagName'; |
|
| 334 | 334 | |
| 335 | - } elseif($char === '>') { |
|
| 336 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 335 | + } elseif($char === '>') { |
|
| 336 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 337 | 337 | Parse error. Emit a U+003C LESS-THAN SIGN character token and a |
| 338 | 338 | U+003E GREATER-THAN SIGN character token. Switch to the data state. */ |
| 339 | - $this->emitToken(array( |
|
| 340 | - 'type' => self::CHARACTR, |
|
| 341 | - 'data' => '<>' |
|
| 342 | - )); |
|
| 339 | + $this->emitToken(array( |
|
| 340 | + 'type' => self::CHARACTR, |
|
| 341 | + 'data' => '<>' |
|
| 342 | + )); |
|
| 343 | 343 | |
| 344 | - $this->state = 'data'; |
|
| 344 | + $this->state = 'data'; |
|
| 345 | 345 | |
| 346 | - } elseif($char === '?') { |
|
| 347 | - /* U+003F QUESTION MARK (?) |
|
| 346 | + } elseif($char === '?') { |
|
| 347 | + /* U+003F QUESTION MARK (?) |
|
| 348 | 348 | Parse error. Switch to the bogus comment state. */ |
| 349 | - $this->state = 'bogusComment'; |
|
| 349 | + $this->state = 'bogusComment'; |
|
| 350 | 350 | |
| 351 | - } else { |
|
| 352 | - /* Anything else |
|
| 351 | + } else { |
|
| 352 | + /* Anything else |
|
| 353 | 353 | Parse error. Emit a U+003C LESS-THAN SIGN character token and |
| 354 | 354 | reconsume the current input character in the data state. */ |
| 355 | - $this->emitToken(array( |
|
| 356 | - 'type' => self::CHARACTR, |
|
| 357 | - 'data' => '<' |
|
| 358 | - )); |
|
| 359 | - |
|
| 360 | - $this->char--; |
|
| 361 | - $this->state = 'data'; |
|
| 362 | - } |
|
| 363 | - break; |
|
| 364 | - } |
|
| 365 | - } |
|
| 366 | - |
|
| 367 | - private function closeTagOpenState() { |
|
| 368 | - $next_node = strtolower($this->characters('A-Za-z', $this->char + 1)); |
|
| 369 | - $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName; |
|
| 370 | - |
|
| 371 | - if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && |
|
| 372 | - (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/', |
|
| 373 | - $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) { |
|
| 374 | - /* If the content model flag is set to the RCDATA or CDATA states then |
|
| 355 | + $this->emitToken(array( |
|
| 356 | + 'type' => self::CHARACTR, |
|
| 357 | + 'data' => '<' |
|
| 358 | + )); |
|
| 359 | + |
|
| 360 | + $this->char--; |
|
| 361 | + $this->state = 'data'; |
|
| 362 | + } |
|
| 363 | + break; |
|
| 364 | + } |
|
| 365 | + } |
|
| 366 | + |
|
| 367 | + private function closeTagOpenState() { |
|
| 368 | + $next_node = strtolower($this->characters('A-Za-z', $this->char + 1)); |
|
| 369 | + $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName; |
|
| 370 | + |
|
| 371 | + if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && |
|
| 372 | + (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/', |
|
| 373 | + $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) { |
|
| 374 | + /* If the content model flag is set to the RCDATA or CDATA states then |
|
| 375 | 375 | examine the next few characters. If they do not match the tag name of |
| 376 | 376 | the last start tag token emitted (case insensitively), or if they do but |
| 377 | 377 | they are not immediately followed by one of the following characters: |
@@ -386,426 +386,426 @@ discard block |
||
| 386 | 386 | ...then there is a parse error. Emit a U+003C LESS-THAN SIGN character |
| 387 | 387 | token, a U+002F SOLIDUS character token, and switch to the data state |
| 388 | 388 | to process the next input character. */ |
| 389 | - $this->emitToken(array( |
|
| 390 | - 'type' => self::CHARACTR, |
|
| 391 | - 'data' => '</' |
|
| 392 | - )); |
|
| 389 | + $this->emitToken(array( |
|
| 390 | + 'type' => self::CHARACTR, |
|
| 391 | + 'data' => '</' |
|
| 392 | + )); |
|
| 393 | 393 | |
| 394 | - $this->state = 'data'; |
|
| 394 | + $this->state = 'data'; |
|
| 395 | 395 | |
| 396 | - } else { |
|
| 397 | - /* Otherwise, if the content model flag is set to the PCDATA state, |
|
| 396 | + } else { |
|
| 397 | + /* Otherwise, if the content model flag is set to the PCDATA state, |
|
| 398 | 398 | or if the next few characters do match that tag name, consume the |
| 399 | 399 | next input character: */ |
| 400 | - $this->char++; |
|
| 401 | - $char = $this->char(); |
|
| 400 | + $this->char++; |
|
| 401 | + $char = $this->char(); |
|
| 402 | 402 | |
| 403 | - if(preg_match('/^[A-Za-z]$/', $char)) { |
|
| 404 | - /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z |
|
| 403 | + if(preg_match('/^[A-Za-z]$/', $char)) { |
|
| 404 | + /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z |
|
| 405 | 405 | Create a new end tag token, set its tag name to the lowercase version |
| 406 | 406 | of the input character (add 0x0020 to the character's code point), then |
| 407 | 407 | switch to the tag name state. (Don't emit the token yet; further details |
| 408 | 408 | will be filled in before it is emitted.) */ |
| 409 | - $this->token = array( |
|
| 410 | - 'name' => strtolower($char), |
|
| 411 | - 'type' => self::ENDTAG |
|
| 412 | - ); |
|
| 409 | + $this->token = array( |
|
| 410 | + 'name' => strtolower($char), |
|
| 411 | + 'type' => self::ENDTAG |
|
| 412 | + ); |
|
| 413 | 413 | |
| 414 | - $this->state = 'tagName'; |
|
| 414 | + $this->state = 'tagName'; |
|
| 415 | 415 | |
| 416 | - } elseif($char === '>') { |
|
| 417 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 416 | + } elseif($char === '>') { |
|
| 417 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 418 | 418 | Parse error. Switch to the data state. */ |
| 419 | - $this->state = 'data'; |
|
| 419 | + $this->state = 'data'; |
|
| 420 | 420 | |
| 421 | - } elseif($this->char === $this->EOF) { |
|
| 422 | - /* EOF |
|
| 421 | + } elseif($this->char === $this->EOF) { |
|
| 422 | + /* EOF |
|
| 423 | 423 | Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F |
| 424 | 424 | SOLIDUS character token. Reconsume the EOF character in the data state. */ |
| 425 | - $this->emitToken(array( |
|
| 426 | - 'type' => self::CHARACTR, |
|
| 427 | - 'data' => '</' |
|
| 428 | - )); |
|
| 429 | - |
|
| 430 | - $this->char--; |
|
| 431 | - $this->state = 'data'; |
|
| 432 | - |
|
| 433 | - } else { |
|
| 434 | - /* Parse error. Switch to the bogus comment state. */ |
|
| 435 | - $this->state = 'bogusComment'; |
|
| 436 | - } |
|
| 437 | - } |
|
| 438 | - } |
|
| 439 | - |
|
| 440 | - private function tagNameState() { |
|
| 441 | - // Consume the next input character: |
|
| 442 | - $this->char++; |
|
| 443 | - $char = $this->character($this->char); |
|
| 444 | - |
|
| 445 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 446 | - /* U+0009 CHARACTER TABULATION |
|
| 425 | + $this->emitToken(array( |
|
| 426 | + 'type' => self::CHARACTR, |
|
| 427 | + 'data' => '</' |
|
| 428 | + )); |
|
| 429 | + |
|
| 430 | + $this->char--; |
|
| 431 | + $this->state = 'data'; |
|
| 432 | + |
|
| 433 | + } else { |
|
| 434 | + /* Parse error. Switch to the bogus comment state. */ |
|
| 435 | + $this->state = 'bogusComment'; |
|
| 436 | + } |
|
| 437 | + } |
|
| 438 | + } |
|
| 439 | + |
|
| 440 | + private function tagNameState() { |
|
| 441 | + // Consume the next input character: |
|
| 442 | + $this->char++; |
|
| 443 | + $char = $this->character($this->char); |
|
| 444 | + |
|
| 445 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 446 | + /* U+0009 CHARACTER TABULATION |
|
| 447 | 447 | U+000A LINE FEED (LF) |
| 448 | 448 | U+000B LINE TABULATION |
| 449 | 449 | U+000C FORM FEED (FF) |
| 450 | 450 | U+0020 SPACE |
| 451 | 451 | Switch to the before attribute name state. */ |
| 452 | - $this->state = 'beforeAttributeName'; |
|
| 452 | + $this->state = 'beforeAttributeName'; |
|
| 453 | 453 | |
| 454 | - } elseif($char === '>') { |
|
| 455 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 454 | + } elseif($char === '>') { |
|
| 455 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 456 | 456 | Emit the current tag token. Switch to the data state. */ |
| 457 | - $this->emitToken($this->token); |
|
| 458 | - $this->state = 'data'; |
|
| 457 | + $this->emitToken($this->token); |
|
| 458 | + $this->state = 'data'; |
|
| 459 | 459 | |
| 460 | - } elseif($this->char === $this->EOF) { |
|
| 461 | - /* EOF |
|
| 460 | + } elseif($this->char === $this->EOF) { |
|
| 461 | + /* EOF |
|
| 462 | 462 | Parse error. Emit the current tag token. Reconsume the EOF |
| 463 | 463 | character in the data state. */ |
| 464 | - $this->emitToken($this->token); |
|
| 464 | + $this->emitToken($this->token); |
|
| 465 | 465 | |
| 466 | - $this->char--; |
|
| 467 | - $this->state = 'data'; |
|
| 466 | + $this->char--; |
|
| 467 | + $this->state = 'data'; |
|
| 468 | 468 | |
| 469 | - } elseif($char === '/') { |
|
| 470 | - /* U+002F SOLIDUS (/) |
|
| 469 | + } elseif($char === '/') { |
|
| 470 | + /* U+002F SOLIDUS (/) |
|
| 471 | 471 | Parse error unless this is a permitted slash. Switch to the before |
| 472 | 472 | attribute name state. */ |
| 473 | - $this->state = 'beforeAttributeName'; |
|
| 473 | + $this->state = 'beforeAttributeName'; |
|
| 474 | 474 | |
| 475 | - } else { |
|
| 476 | - /* Anything else |
|
| 475 | + } else { |
|
| 476 | + /* Anything else |
|
| 477 | 477 | Append the current input character to the current tag token's tag name. |
| 478 | 478 | Stay in the tag name state. */ |
| 479 | - $this->token['name'] .= strtolower($char); |
|
| 480 | - $this->state = 'tagName'; |
|
| 481 | - } |
|
| 482 | - } |
|
| 483 | - |
|
| 484 | - private function beforeAttributeNameState() { |
|
| 485 | - // Consume the next input character: |
|
| 486 | - $this->char++; |
|
| 487 | - $char = $this->character($this->char); |
|
| 488 | - |
|
| 489 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 490 | - /* U+0009 CHARACTER TABULATION |
|
| 479 | + $this->token['name'] .= strtolower($char); |
|
| 480 | + $this->state = 'tagName'; |
|
| 481 | + } |
|
| 482 | + } |
|
| 483 | + |
|
| 484 | + private function beforeAttributeNameState() { |
|
| 485 | + // Consume the next input character: |
|
| 486 | + $this->char++; |
|
| 487 | + $char = $this->character($this->char); |
|
| 488 | + |
|
| 489 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 490 | + /* U+0009 CHARACTER TABULATION |
|
| 491 | 491 | U+000A LINE FEED (LF) |
| 492 | 492 | U+000B LINE TABULATION |
| 493 | 493 | U+000C FORM FEED (FF) |
| 494 | 494 | U+0020 SPACE |
| 495 | 495 | Stay in the before attribute name state. */ |
| 496 | - $this->state = 'beforeAttributeName'; |
|
| 496 | + $this->state = 'beforeAttributeName'; |
|
| 497 | 497 | |
| 498 | - } elseif($char === '>') { |
|
| 499 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 498 | + } elseif($char === '>') { |
|
| 499 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 500 | 500 | Emit the current tag token. Switch to the data state. */ |
| 501 | - $this->emitToken($this->token); |
|
| 502 | - $this->state = 'data'; |
|
| 501 | + $this->emitToken($this->token); |
|
| 502 | + $this->state = 'data'; |
|
| 503 | 503 | |
| 504 | - } elseif($char === '/') { |
|
| 505 | - /* U+002F SOLIDUS (/) |
|
| 504 | + } elseif($char === '/') { |
|
| 505 | + /* U+002F SOLIDUS (/) |
|
| 506 | 506 | Parse error unless this is a permitted slash. Stay in the before |
| 507 | 507 | attribute name state. */ |
| 508 | - $this->state = 'beforeAttributeName'; |
|
| 508 | + $this->state = 'beforeAttributeName'; |
|
| 509 | 509 | |
| 510 | - } elseif($this->char === $this->EOF) { |
|
| 511 | - /* EOF |
|
| 510 | + } elseif($this->char === $this->EOF) { |
|
| 511 | + /* EOF |
|
| 512 | 512 | Parse error. Emit the current tag token. Reconsume the EOF |
| 513 | 513 | character in the data state. */ |
| 514 | - $this->emitToken($this->token); |
|
| 514 | + $this->emitToken($this->token); |
|
| 515 | 515 | |
| 516 | - $this->char--; |
|
| 517 | - $this->state = 'data'; |
|
| 516 | + $this->char--; |
|
| 517 | + $this->state = 'data'; |
|
| 518 | 518 | |
| 519 | - } else { |
|
| 520 | - /* Anything else |
|
| 519 | + } else { |
|
| 520 | + /* Anything else |
|
| 521 | 521 | Start a new attribute in the current tag token. Set that attribute's |
| 522 | 522 | name to the current input character, and its value to the empty string. |
| 523 | 523 | Switch to the attribute name state. */ |
| 524 | - $this->token['attr'][] = array( |
|
| 525 | - 'name' => strtolower($char), |
|
| 526 | - 'value' => null |
|
| 527 | - ); |
|
| 528 | - |
|
| 529 | - $this->state = 'attributeName'; |
|
| 530 | - } |
|
| 531 | - } |
|
| 532 | - |
|
| 533 | - private function attributeNameState() { |
|
| 534 | - // Consume the next input character: |
|
| 535 | - $this->char++; |
|
| 536 | - $char = $this->character($this->char); |
|
| 537 | - |
|
| 538 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 539 | - /* U+0009 CHARACTER TABULATION |
|
| 524 | + $this->token['attr'][] = array( |
|
| 525 | + 'name' => strtolower($char), |
|
| 526 | + 'value' => null |
|
| 527 | + ); |
|
| 528 | + |
|
| 529 | + $this->state = 'attributeName'; |
|
| 530 | + } |
|
| 531 | + } |
|
| 532 | + |
|
| 533 | + private function attributeNameState() { |
|
| 534 | + // Consume the next input character: |
|
| 535 | + $this->char++; |
|
| 536 | + $char = $this->character($this->char); |
|
| 537 | + |
|
| 538 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 539 | + /* U+0009 CHARACTER TABULATION |
|
| 540 | 540 | U+000A LINE FEED (LF) |
| 541 | 541 | U+000B LINE TABULATION |
| 542 | 542 | U+000C FORM FEED (FF) |
| 543 | 543 | U+0020 SPACE |
| 544 | 544 | Stay in the before attribute name state. */ |
| 545 | - $this->state = 'afterAttributeName'; |
|
| 545 | + $this->state = 'afterAttributeName'; |
|
| 546 | 546 | |
| 547 | - } elseif($char === '=') { |
|
| 548 | - /* U+003D EQUALS SIGN (=) |
|
| 547 | + } elseif($char === '=') { |
|
| 548 | + /* U+003D EQUALS SIGN (=) |
|
| 549 | 549 | Switch to the before attribute value state. */ |
| 550 | - $this->state = 'beforeAttributeValue'; |
|
| 550 | + $this->state = 'beforeAttributeValue'; |
|
| 551 | 551 | |
| 552 | - } elseif($char === '>') { |
|
| 553 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 552 | + } elseif($char === '>') { |
|
| 553 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 554 | 554 | Emit the current tag token. Switch to the data state. */ |
| 555 | - $this->emitToken($this->token); |
|
| 556 | - $this->state = 'data'; |
|
| 555 | + $this->emitToken($this->token); |
|
| 556 | + $this->state = 'data'; |
|
| 557 | 557 | |
| 558 | - } elseif($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 559 | - /* U+002F SOLIDUS (/) |
|
| 558 | + } elseif($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 559 | + /* U+002F SOLIDUS (/) |
|
| 560 | 560 | Parse error unless this is a permitted slash. Switch to the before |
| 561 | 561 | attribute name state. */ |
| 562 | - $this->state = 'beforeAttributeName'; |
|
| 562 | + $this->state = 'beforeAttributeName'; |
|
| 563 | 563 | |
| 564 | - } elseif($this->char === $this->EOF) { |
|
| 565 | - /* EOF |
|
| 564 | + } elseif($this->char === $this->EOF) { |
|
| 565 | + /* EOF |
|
| 566 | 566 | Parse error. Emit the current tag token. Reconsume the EOF |
| 567 | 567 | character in the data state. */ |
| 568 | - $this->emitToken($this->token); |
|
| 568 | + $this->emitToken($this->token); |
|
| 569 | 569 | |
| 570 | - $this->char--; |
|
| 571 | - $this->state = 'data'; |
|
| 570 | + $this->char--; |
|
| 571 | + $this->state = 'data'; |
|
| 572 | 572 | |
| 573 | - } else { |
|
| 574 | - /* Anything else |
|
| 573 | + } else { |
|
| 574 | + /* Anything else |
|
| 575 | 575 | Append the current input character to the current attribute's name. |
| 576 | 576 | Stay in the attribute name state. */ |
| 577 | - $last = count($this->token['attr']) - 1; |
|
| 578 | - $this->token['attr'][$last]['name'] .= strtolower($char); |
|
| 577 | + $last = count($this->token['attr']) - 1; |
|
| 578 | + $this->token['attr'][$last]['name'] .= strtolower($char); |
|
| 579 | 579 | |
| 580 | - $this->state = 'attributeName'; |
|
| 581 | - } |
|
| 582 | - } |
|
| 580 | + $this->state = 'attributeName'; |
|
| 581 | + } |
|
| 582 | + } |
|
| 583 | 583 | |
| 584 | - private function afterAttributeNameState() { |
|
| 585 | - // Consume the next input character: |
|
| 586 | - $this->char++; |
|
| 587 | - $char = $this->character($this->char); |
|
| 584 | + private function afterAttributeNameState() { |
|
| 585 | + // Consume the next input character: |
|
| 586 | + $this->char++; |
|
| 587 | + $char = $this->character($this->char); |
|
| 588 | 588 | |
| 589 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 590 | - /* U+0009 CHARACTER TABULATION |
|
| 589 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 590 | + /* U+0009 CHARACTER TABULATION |
|
| 591 | 591 | U+000A LINE FEED (LF) |
| 592 | 592 | U+000B LINE TABULATION |
| 593 | 593 | U+000C FORM FEED (FF) |
| 594 | 594 | U+0020 SPACE |
| 595 | 595 | Stay in the after attribute name state. */ |
| 596 | - $this->state = 'afterAttributeName'; |
|
| 596 | + $this->state = 'afterAttributeName'; |
|
| 597 | 597 | |
| 598 | - } elseif($char === '=') { |
|
| 599 | - /* U+003D EQUALS SIGN (=) |
|
| 598 | + } elseif($char === '=') { |
|
| 599 | + /* U+003D EQUALS SIGN (=) |
|
| 600 | 600 | Switch to the before attribute value state. */ |
| 601 | - $this->state = 'beforeAttributeValue'; |
|
| 601 | + $this->state = 'beforeAttributeValue'; |
|
| 602 | 602 | |
| 603 | - } elseif($char === '>') { |
|
| 604 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 603 | + } elseif($char === '>') { |
|
| 604 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 605 | 605 | Emit the current tag token. Switch to the data state. */ |
| 606 | - $this->emitToken($this->token); |
|
| 607 | - $this->state = 'data'; |
|
| 606 | + $this->emitToken($this->token); |
|
| 607 | + $this->state = 'data'; |
|
| 608 | 608 | |
| 609 | - } elseif($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 610 | - /* U+002F SOLIDUS (/) |
|
| 609 | + } elseif($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 610 | + /* U+002F SOLIDUS (/) |
|
| 611 | 611 | Parse error unless this is a permitted slash. Switch to the |
| 612 | 612 | before attribute name state. */ |
| 613 | - $this->state = 'beforeAttributeName'; |
|
| 613 | + $this->state = 'beforeAttributeName'; |
|
| 614 | 614 | |
| 615 | - } elseif($this->char === $this->EOF) { |
|
| 616 | - /* EOF |
|
| 615 | + } elseif($this->char === $this->EOF) { |
|
| 616 | + /* EOF |
|
| 617 | 617 | Parse error. Emit the current tag token. Reconsume the EOF |
| 618 | 618 | character in the data state. */ |
| 619 | - $this->emitToken($this->token); |
|
| 619 | + $this->emitToken($this->token); |
|
| 620 | 620 | |
| 621 | - $this->char--; |
|
| 622 | - $this->state = 'data'; |
|
| 621 | + $this->char--; |
|
| 622 | + $this->state = 'data'; |
|
| 623 | 623 | |
| 624 | - } else { |
|
| 625 | - /* Anything else |
|
| 624 | + } else { |
|
| 625 | + /* Anything else |
|
| 626 | 626 | Start a new attribute in the current tag token. Set that attribute's |
| 627 | 627 | name to the current input character, and its value to the empty string. |
| 628 | 628 | Switch to the attribute name state. */ |
| 629 | - $this->token['attr'][] = array( |
|
| 630 | - 'name' => strtolower($char), |
|
| 631 | - 'value' => null |
|
| 632 | - ); |
|
| 633 | - |
|
| 634 | - $this->state = 'attributeName'; |
|
| 635 | - } |
|
| 636 | - } |
|
| 637 | - |
|
| 638 | - private function beforeAttributeValueState() { |
|
| 639 | - // Consume the next input character: |
|
| 640 | - $this->char++; |
|
| 641 | - $char = $this->character($this->char); |
|
| 642 | - |
|
| 643 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 644 | - /* U+0009 CHARACTER TABULATION |
|
| 629 | + $this->token['attr'][] = array( |
|
| 630 | + 'name' => strtolower($char), |
|
| 631 | + 'value' => null |
|
| 632 | + ); |
|
| 633 | + |
|
| 634 | + $this->state = 'attributeName'; |
|
| 635 | + } |
|
| 636 | + } |
|
| 637 | + |
|
| 638 | + private function beforeAttributeValueState() { |
|
| 639 | + // Consume the next input character: |
|
| 640 | + $this->char++; |
|
| 641 | + $char = $this->character($this->char); |
|
| 642 | + |
|
| 643 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 644 | + /* U+0009 CHARACTER TABULATION |
|
| 645 | 645 | U+000A LINE FEED (LF) |
| 646 | 646 | U+000B LINE TABULATION |
| 647 | 647 | U+000C FORM FEED (FF) |
| 648 | 648 | U+0020 SPACE |
| 649 | 649 | Stay in the before attribute value state. */ |
| 650 | - $this->state = 'beforeAttributeValue'; |
|
| 650 | + $this->state = 'beforeAttributeValue'; |
|
| 651 | 651 | |
| 652 | - } elseif($char === '"') { |
|
| 653 | - /* U+0022 QUOTATION MARK (") |
|
| 652 | + } elseif($char === '"') { |
|
| 653 | + /* U+0022 QUOTATION MARK (") |
|
| 654 | 654 | Switch to the attribute value (double-quoted) state. */ |
| 655 | - $this->state = 'attributeValueDoubleQuoted'; |
|
| 655 | + $this->state = 'attributeValueDoubleQuoted'; |
|
| 656 | 656 | |
| 657 | - } elseif($char === '&') { |
|
| 658 | - /* U+0026 AMPERSAND (&) |
|
| 657 | + } elseif($char === '&') { |
|
| 658 | + /* U+0026 AMPERSAND (&) |
|
| 659 | 659 | Switch to the attribute value (unquoted) state and reconsume |
| 660 | 660 | this input character. */ |
| 661 | - $this->char--; |
|
| 662 | - $this->state = 'attributeValueUnquoted'; |
|
| 661 | + $this->char--; |
|
| 662 | + $this->state = 'attributeValueUnquoted'; |
|
| 663 | 663 | |
| 664 | - } elseif($char === '\'') { |
|
| 665 | - /* U+0027 APOSTROPHE (') |
|
| 664 | + } elseif($char === '\'') { |
|
| 665 | + /* U+0027 APOSTROPHE (') |
|
| 666 | 666 | Switch to the attribute value (single-quoted) state. */ |
| 667 | - $this->state = 'attributeValueSingleQuoted'; |
|
| 667 | + $this->state = 'attributeValueSingleQuoted'; |
|
| 668 | 668 | |
| 669 | - } elseif($char === '>') { |
|
| 670 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 669 | + } elseif($char === '>') { |
|
| 670 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 671 | 671 | Emit the current tag token. Switch to the data state. */ |
| 672 | - $this->emitToken($this->token); |
|
| 673 | - $this->state = 'data'; |
|
| 672 | + $this->emitToken($this->token); |
|
| 673 | + $this->state = 'data'; |
|
| 674 | 674 | |
| 675 | - } else { |
|
| 676 | - /* Anything else |
|
| 675 | + } else { |
|
| 676 | + /* Anything else |
|
| 677 | 677 | Append the current input character to the current attribute's value. |
| 678 | 678 | Switch to the attribute value (unquoted) state. */ |
| 679 | - $last = count($this->token['attr']) - 1; |
|
| 680 | - $this->token['attr'][$last]['value'] .= $char; |
|
| 679 | + $last = count($this->token['attr']) - 1; |
|
| 680 | + $this->token['attr'][$last]['value'] .= $char; |
|
| 681 | 681 | |
| 682 | - $this->state = 'attributeValueUnquoted'; |
|
| 683 | - } |
|
| 684 | - } |
|
| 682 | + $this->state = 'attributeValueUnquoted'; |
|
| 683 | + } |
|
| 684 | + } |
|
| 685 | 685 | |
| 686 | - private function attributeValueDoubleQuotedState() { |
|
| 687 | - // Consume the next input character: |
|
| 688 | - $this->char++; |
|
| 689 | - $char = $this->character($this->char); |
|
| 686 | + private function attributeValueDoubleQuotedState() { |
|
| 687 | + // Consume the next input character: |
|
| 688 | + $this->char++; |
|
| 689 | + $char = $this->character($this->char); |
|
| 690 | 690 | |
| 691 | - if($char === '"') { |
|
| 692 | - /* U+0022 QUOTATION MARK (") |
|
| 691 | + if($char === '"') { |
|
| 692 | + /* U+0022 QUOTATION MARK (") |
|
| 693 | 693 | Switch to the before attribute name state. */ |
| 694 | - $this->state = 'beforeAttributeName'; |
|
| 694 | + $this->state = 'beforeAttributeName'; |
|
| 695 | 695 | |
| 696 | - } elseif($char === '&') { |
|
| 697 | - /* U+0026 AMPERSAND (&) |
|
| 696 | + } elseif($char === '&') { |
|
| 697 | + /* U+0026 AMPERSAND (&) |
|
| 698 | 698 | Switch to the entity in attribute value state. */ |
| 699 | - $this->entityInAttributeValueState('double'); |
|
| 699 | + $this->entityInAttributeValueState('double'); |
|
| 700 | 700 | |
| 701 | - } elseif($this->char === $this->EOF) { |
|
| 702 | - /* EOF |
|
| 701 | + } elseif($this->char === $this->EOF) { |
|
| 702 | + /* EOF |
|
| 703 | 703 | Parse error. Emit the current tag token. Reconsume the character |
| 704 | 704 | in the data state. */ |
| 705 | - $this->emitToken($this->token); |
|
| 705 | + $this->emitToken($this->token); |
|
| 706 | 706 | |
| 707 | - $this->char--; |
|
| 708 | - $this->state = 'data'; |
|
| 707 | + $this->char--; |
|
| 708 | + $this->state = 'data'; |
|
| 709 | 709 | |
| 710 | - } else { |
|
| 711 | - /* Anything else |
|
| 710 | + } else { |
|
| 711 | + /* Anything else |
|
| 712 | 712 | Append the current input character to the current attribute's value. |
| 713 | 713 | Stay in the attribute value (double-quoted) state. */ |
| 714 | - $last = count($this->token['attr']) - 1; |
|
| 715 | - $this->token['attr'][$last]['value'] .= $char; |
|
| 714 | + $last = count($this->token['attr']) - 1; |
|
| 715 | + $this->token['attr'][$last]['value'] .= $char; |
|
| 716 | 716 | |
| 717 | - $this->state = 'attributeValueDoubleQuoted'; |
|
| 718 | - } |
|
| 719 | - } |
|
| 717 | + $this->state = 'attributeValueDoubleQuoted'; |
|
| 718 | + } |
|
| 719 | + } |
|
| 720 | 720 | |
| 721 | - private function attributeValueSingleQuotedState() { |
|
| 722 | - // Consume the next input character: |
|
| 723 | - $this->char++; |
|
| 724 | - $char = $this->character($this->char); |
|
| 721 | + private function attributeValueSingleQuotedState() { |
|
| 722 | + // Consume the next input character: |
|
| 723 | + $this->char++; |
|
| 724 | + $char = $this->character($this->char); |
|
| 725 | 725 | |
| 726 | - if($char === '\'') { |
|
| 727 | - /* U+0022 QUOTATION MARK (') |
|
| 726 | + if($char === '\'') { |
|
| 727 | + /* U+0022 QUOTATION MARK (') |
|
| 728 | 728 | Switch to the before attribute name state. */ |
| 729 | - $this->state = 'beforeAttributeName'; |
|
| 729 | + $this->state = 'beforeAttributeName'; |
|
| 730 | 730 | |
| 731 | - } elseif($char === '&') { |
|
| 732 | - /* U+0026 AMPERSAND (&) |
|
| 731 | + } elseif($char === '&') { |
|
| 732 | + /* U+0026 AMPERSAND (&) |
|
| 733 | 733 | Switch to the entity in attribute value state. */ |
| 734 | - $this->entityInAttributeValueState('single'); |
|
| 734 | + $this->entityInAttributeValueState('single'); |
|
| 735 | 735 | |
| 736 | - } elseif($this->char === $this->EOF) { |
|
| 737 | - /* EOF |
|
| 736 | + } elseif($this->char === $this->EOF) { |
|
| 737 | + /* EOF |
|
| 738 | 738 | Parse error. Emit the current tag token. Reconsume the character |
| 739 | 739 | in the data state. */ |
| 740 | - $this->emitToken($this->token); |
|
| 740 | + $this->emitToken($this->token); |
|
| 741 | 741 | |
| 742 | - $this->char--; |
|
| 743 | - $this->state = 'data'; |
|
| 742 | + $this->char--; |
|
| 743 | + $this->state = 'data'; |
|
| 744 | 744 | |
| 745 | - } else { |
|
| 746 | - /* Anything else |
|
| 745 | + } else { |
|
| 746 | + /* Anything else |
|
| 747 | 747 | Append the current input character to the current attribute's value. |
| 748 | 748 | Stay in the attribute value (single-quoted) state. */ |
| 749 | - $last = count($this->token['attr']) - 1; |
|
| 750 | - $this->token['attr'][$last]['value'] .= $char; |
|
| 749 | + $last = count($this->token['attr']) - 1; |
|
| 750 | + $this->token['attr'][$last]['value'] .= $char; |
|
| 751 | 751 | |
| 752 | - $this->state = 'attributeValueSingleQuoted'; |
|
| 753 | - } |
|
| 754 | - } |
|
| 752 | + $this->state = 'attributeValueSingleQuoted'; |
|
| 753 | + } |
|
| 754 | + } |
|
| 755 | 755 | |
| 756 | - private function attributeValueUnquotedState() { |
|
| 757 | - // Consume the next input character: |
|
| 758 | - $this->char++; |
|
| 759 | - $char = $this->character($this->char); |
|
| 756 | + private function attributeValueUnquotedState() { |
|
| 757 | + // Consume the next input character: |
|
| 758 | + $this->char++; |
|
| 759 | + $char = $this->character($this->char); |
|
| 760 | 760 | |
| 761 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 762 | - /* U+0009 CHARACTER TABULATION |
|
| 761 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 762 | + /* U+0009 CHARACTER TABULATION |
|
| 763 | 763 | U+000A LINE FEED (LF) |
| 764 | 764 | U+000B LINE TABULATION |
| 765 | 765 | U+000C FORM FEED (FF) |
| 766 | 766 | U+0020 SPACE |
| 767 | 767 | Switch to the before attribute name state. */ |
| 768 | - $this->state = 'beforeAttributeName'; |
|
| 768 | + $this->state = 'beforeAttributeName'; |
|
| 769 | 769 | |
| 770 | - } elseif($char === '&') { |
|
| 771 | - /* U+0026 AMPERSAND (&) |
|
| 770 | + } elseif($char === '&') { |
|
| 771 | + /* U+0026 AMPERSAND (&) |
|
| 772 | 772 | Switch to the entity in attribute value state. */ |
| 773 | - $this->entityInAttributeValueState(); |
|
| 773 | + $this->entityInAttributeValueState(); |
|
| 774 | 774 | |
| 775 | - } elseif($char === '>') { |
|
| 776 | - /* U+003E GREATER-THAN SIGN (>) |
|
| 775 | + } elseif($char === '>') { |
|
| 776 | + /* U+003E GREATER-THAN SIGN (>) |
|
| 777 | 777 | Emit the current tag token. Switch to the data state. */ |
| 778 | - $this->emitToken($this->token); |
|
| 779 | - $this->state = 'data'; |
|
| 778 | + $this->emitToken($this->token); |
|
| 779 | + $this->state = 'data'; |
|
| 780 | 780 | |
| 781 | - } else { |
|
| 782 | - /* Anything else |
|
| 781 | + } else { |
|
| 782 | + /* Anything else |
|
| 783 | 783 | Append the current input character to the current attribute's value. |
| 784 | 784 | Stay in the attribute value (unquoted) state. */ |
| 785 | - $last = count($this->token['attr']) - 1; |
|
| 786 | - $this->token['attr'][$last]['value'] .= $char; |
|
| 787 | - |
|
| 788 | - $this->state = 'attributeValueUnquoted'; |
|
| 789 | - } |
|
| 790 | - } |
|
| 791 | - |
|
| 792 | - private function entityInAttributeValueState() { |
|
| 793 | - // Attempt to consume an entity. |
|
| 794 | - $entity = $this->entity(); |
|
| 795 | - |
|
| 796 | - // If nothing is returned, append a U+0026 AMPERSAND character to the |
|
| 797 | - // current attribute's value. Otherwise, emit the character token that |
|
| 798 | - // was returned. |
|
| 799 | - $char = (!$entity) |
|
| 800 | - ? '&' |
|
| 801 | - : $entity; |
|
| 802 | - |
|
| 803 | - $last = count($this->token['attr']) - 1; |
|
| 804 | - $this->token['attr'][$last]['value'] .= $char; |
|
| 805 | - } |
|
| 806 | - |
|
| 807 | - private function bogusCommentState() { |
|
| 808 | - /* Consume every character up to the first U+003E GREATER-THAN SIGN |
|
| 785 | + $last = count($this->token['attr']) - 1; |
|
| 786 | + $this->token['attr'][$last]['value'] .= $char; |
|
| 787 | + |
|
| 788 | + $this->state = 'attributeValueUnquoted'; |
|
| 789 | + } |
|
| 790 | + } |
|
| 791 | + |
|
| 792 | + private function entityInAttributeValueState() { |
|
| 793 | + // Attempt to consume an entity. |
|
| 794 | + $entity = $this->entity(); |
|
| 795 | + |
|
| 796 | + // If nothing is returned, append a U+0026 AMPERSAND character to the |
|
| 797 | + // current attribute's value. Otherwise, emit the character token that |
|
| 798 | + // was returned. |
|
| 799 | + $char = (!$entity) |
|
| 800 | + ? '&' |
|
| 801 | + : $entity; |
|
| 802 | + |
|
| 803 | + $last = count($this->token['attr']) - 1; |
|
| 804 | + $this->token['attr'][$last]['value'] .= $char; |
|
| 805 | + } |
|
| 806 | + |
|
| 807 | + private function bogusCommentState() { |
|
| 808 | + /* Consume every character up to the first U+003E GREATER-THAN SIGN |
|
| 809 | 809 | character (>) or the end of the file (EOF), whichever comes first. Emit |
| 810 | 810 | a comment token whose data is the concatenation of all the characters |
| 811 | 811 | starting from and including the character that caused the state machine |
@@ -813,446 +813,446 @@ discard block |
||
| 813 | 813 | consumed character before the U+003E character, if any, or up to the |
| 814 | 814 | end of the file otherwise. (If the comment was started by the end of |
| 815 | 815 | the file (EOF), the token is empty.) */ |
| 816 | - $data = $this->characters('^>', $this->char); |
|
| 817 | - $this->emitToken(array( |
|
| 818 | - 'data' => $data, |
|
| 819 | - 'type' => self::COMMENT |
|
| 820 | - )); |
|
| 816 | + $data = $this->characters('^>', $this->char); |
|
| 817 | + $this->emitToken(array( |
|
| 818 | + 'data' => $data, |
|
| 819 | + 'type' => self::COMMENT |
|
| 820 | + )); |
|
| 821 | 821 | |
| 822 | - $this->char += strlen($data); |
|
| 822 | + $this->char += strlen($data); |
|
| 823 | 823 | |
| 824 | - /* Switch to the data state. */ |
|
| 825 | - $this->state = 'data'; |
|
| 824 | + /* Switch to the data state. */ |
|
| 825 | + $this->state = 'data'; |
|
| 826 | 826 | |
| 827 | - /* If the end of the file was reached, reconsume the EOF character. */ |
|
| 828 | - if($this->char === $this->EOF) { |
|
| 829 | - $this->char = $this->EOF - 1; |
|
| 830 | - } |
|
| 831 | - } |
|
| 827 | + /* If the end of the file was reached, reconsume the EOF character. */ |
|
| 828 | + if($this->char === $this->EOF) { |
|
| 829 | + $this->char = $this->EOF - 1; |
|
| 830 | + } |
|
| 831 | + } |
|
| 832 | 832 | |
| 833 | - private function markupDeclarationOpenState() { |
|
| 834 | - /* If the next two characters are both U+002D HYPHEN-MINUS (-) |
|
| 833 | + private function markupDeclarationOpenState() { |
|
| 834 | + /* If the next two characters are both U+002D HYPHEN-MINUS (-) |
|
| 835 | 835 | characters, consume those two characters, create a comment token whose |
| 836 | 836 | data is the empty string, and switch to the comment state. */ |
| 837 | - if($this->character($this->char + 1, 2) === '--') { |
|
| 838 | - $this->char += 2; |
|
| 839 | - $this->state = 'comment'; |
|
| 840 | - $this->token = array( |
|
| 841 | - 'data' => null, |
|
| 842 | - 'type' => self::COMMENT |
|
| 843 | - ); |
|
| 844 | - |
|
| 845 | - /* Otherwise if the next seven chacacters are a case-insensitive match |
|
| 837 | + if($this->character($this->char + 1, 2) === '--') { |
|
| 838 | + $this->char += 2; |
|
| 839 | + $this->state = 'comment'; |
|
| 840 | + $this->token = array( |
|
| 841 | + 'data' => null, |
|
| 842 | + 'type' => self::COMMENT |
|
| 843 | + ); |
|
| 844 | + |
|
| 845 | + /* Otherwise if the next seven chacacters are a case-insensitive match |
|
| 846 | 846 | for the word "DOCTYPE", then consume those characters and switch to the |
| 847 | 847 | DOCTYPE state. */ |
| 848 | - } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') { |
|
| 849 | - $this->char += 7; |
|
| 850 | - $this->state = 'doctype'; |
|
| 848 | + } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') { |
|
| 849 | + $this->char += 7; |
|
| 850 | + $this->state = 'doctype'; |
|
| 851 | 851 | |
| 852 | - /* Otherwise, is is a parse error. Switch to the bogus comment state. |
|
| 852 | + /* Otherwise, is is a parse error. Switch to the bogus comment state. |
|
| 853 | 853 | The next character that is consumed, if any, is the first character |
| 854 | 854 | that will be in the comment. */ |
| 855 | - } else { |
|
| 856 | - $this->char++; |
|
| 857 | - $this->state = 'bogusComment'; |
|
| 858 | - } |
|
| 859 | - } |
|
| 860 | - |
|
| 861 | - private function commentState() { |
|
| 862 | - /* Consume the next input character: */ |
|
| 863 | - $this->char++; |
|
| 864 | - $char = $this->char(); |
|
| 865 | - |
|
| 866 | - /* U+002D HYPHEN-MINUS (-) */ |
|
| 867 | - if($char === '-') { |
|
| 868 | - /* Switch to the comment dash state */ |
|
| 869 | - $this->state = 'commentDash'; |
|
| 870 | - |
|
| 871 | - /* EOF */ |
|
| 872 | - } elseif($this->char === $this->EOF) { |
|
| 873 | - /* Parse error. Emit the comment token. Reconsume the EOF character |
|
| 855 | + } else { |
|
| 856 | + $this->char++; |
|
| 857 | + $this->state = 'bogusComment'; |
|
| 858 | + } |
|
| 859 | + } |
|
| 860 | + |
|
| 861 | + private function commentState() { |
|
| 862 | + /* Consume the next input character: */ |
|
| 863 | + $this->char++; |
|
| 864 | + $char = $this->char(); |
|
| 865 | + |
|
| 866 | + /* U+002D HYPHEN-MINUS (-) */ |
|
| 867 | + if($char === '-') { |
|
| 868 | + /* Switch to the comment dash state */ |
|
| 869 | + $this->state = 'commentDash'; |
|
| 870 | + |
|
| 871 | + /* EOF */ |
|
| 872 | + } elseif($this->char === $this->EOF) { |
|
| 873 | + /* Parse error. Emit the comment token. Reconsume the EOF character |
|
| 874 | 874 | in the data state. */ |
| 875 | - $this->emitToken($this->token); |
|
| 876 | - $this->char--; |
|
| 877 | - $this->state = 'data'; |
|
| 875 | + $this->emitToken($this->token); |
|
| 876 | + $this->char--; |
|
| 877 | + $this->state = 'data'; |
|
| 878 | 878 | |
| 879 | - /* Anything else */ |
|
| 880 | - } else { |
|
| 881 | - /* Append the input character to the comment token's data. Stay in |
|
| 879 | + /* Anything else */ |
|
| 880 | + } else { |
|
| 881 | + /* Append the input character to the comment token's data. Stay in |
|
| 882 | 882 | the comment state. */ |
| 883 | - $this->token['data'] .= $char; |
|
| 884 | - } |
|
| 885 | - } |
|
| 886 | - |
|
| 887 | - private function commentDashState() { |
|
| 888 | - /* Consume the next input character: */ |
|
| 889 | - $this->char++; |
|
| 890 | - $char = $this->char(); |
|
| 891 | - |
|
| 892 | - /* U+002D HYPHEN-MINUS (-) */ |
|
| 893 | - if($char === '-') { |
|
| 894 | - /* Switch to the comment end state */ |
|
| 895 | - $this->state = 'commentEnd'; |
|
| 896 | - |
|
| 897 | - /* EOF */ |
|
| 898 | - } elseif($this->char === $this->EOF) { |
|
| 899 | - /* Parse error. Emit the comment token. Reconsume the EOF character |
|
| 883 | + $this->token['data'] .= $char; |
|
| 884 | + } |
|
| 885 | + } |
|
| 886 | + |
|
| 887 | + private function commentDashState() { |
|
| 888 | + /* Consume the next input character: */ |
|
| 889 | + $this->char++; |
|
| 890 | + $char = $this->char(); |
|
| 891 | + |
|
| 892 | + /* U+002D HYPHEN-MINUS (-) */ |
|
| 893 | + if($char === '-') { |
|
| 894 | + /* Switch to the comment end state */ |
|
| 895 | + $this->state = 'commentEnd'; |
|
| 896 | + |
|
| 897 | + /* EOF */ |
|
| 898 | + } elseif($this->char === $this->EOF) { |
|
| 899 | + /* Parse error. Emit the comment token. Reconsume the EOF character |
|
| 900 | 900 | in the data state. */ |
| 901 | - $this->emitToken($this->token); |
|
| 902 | - $this->char--; |
|
| 903 | - $this->state = 'data'; |
|
| 901 | + $this->emitToken($this->token); |
|
| 902 | + $this->char--; |
|
| 903 | + $this->state = 'data'; |
|
| 904 | 904 | |
| 905 | - /* Anything else */ |
|
| 906 | - } else { |
|
| 907 | - /* Append a U+002D HYPHEN-MINUS (-) character and the input |
|
| 905 | + /* Anything else */ |
|
| 906 | + } else { |
|
| 907 | + /* Append a U+002D HYPHEN-MINUS (-) character and the input |
|
| 908 | 908 | character to the comment token's data. Switch to the comment state. */ |
| 909 | - $this->token['data'] .= '-'.$char; |
|
| 910 | - $this->state = 'comment'; |
|
| 911 | - } |
|
| 912 | - } |
|
| 913 | - |
|
| 914 | - private function commentEndState() { |
|
| 915 | - /* Consume the next input character: */ |
|
| 916 | - $this->char++; |
|
| 917 | - $char = $this->char(); |
|
| 918 | - |
|
| 919 | - if($char === '>') { |
|
| 920 | - $this->emitToken($this->token); |
|
| 921 | - $this->state = 'data'; |
|
| 922 | - |
|
| 923 | - } elseif($char === '-') { |
|
| 924 | - $this->token['data'] .= '-'; |
|
| 925 | - |
|
| 926 | - } elseif($this->char === $this->EOF) { |
|
| 927 | - $this->emitToken($this->token); |
|
| 928 | - $this->char--; |
|
| 929 | - $this->state = 'data'; |
|
| 930 | - |
|
| 931 | - } else { |
|
| 932 | - $this->token['data'] .= '--'.$char; |
|
| 933 | - $this->state = 'comment'; |
|
| 934 | - } |
|
| 935 | - } |
|
| 936 | - |
|
| 937 | - private function doctypeState() { |
|
| 938 | - /* Consume the next input character: */ |
|
| 939 | - $this->char++; |
|
| 940 | - $char = $this->char(); |
|
| 941 | - |
|
| 942 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 943 | - $this->state = 'beforeDoctypeName'; |
|
| 944 | - |
|
| 945 | - } else { |
|
| 946 | - $this->char--; |
|
| 947 | - $this->state = 'beforeDoctypeName'; |
|
| 948 | - } |
|
| 949 | - } |
|
| 950 | - |
|
| 951 | - private function beforeDoctypeNameState() { |
|
| 952 | - /* Consume the next input character: */ |
|
| 953 | - $this->char++; |
|
| 954 | - $char = $this->char(); |
|
| 955 | - |
|
| 956 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 957 | - // Stay in the before DOCTYPE name state. |
|
| 958 | - |
|
| 959 | - } elseif(preg_match('/^[a-z]$/', $char)) { |
|
| 960 | - $this->token = array( |
|
| 961 | - 'name' => strtoupper($char), |
|
| 962 | - 'type' => self::DOCTYPE, |
|
| 963 | - 'error' => true |
|
| 964 | - ); |
|
| 965 | - |
|
| 966 | - $this->state = 'doctypeName'; |
|
| 967 | - |
|
| 968 | - } elseif($char === '>') { |
|
| 969 | - $this->emitToken(array( |
|
| 970 | - 'name' => null, |
|
| 971 | - 'type' => self::DOCTYPE, |
|
| 972 | - 'error' => true |
|
| 973 | - )); |
|
| 974 | - |
|
| 975 | - $this->state = 'data'; |
|
| 976 | - |
|
| 977 | - } elseif($this->char === $this->EOF) { |
|
| 978 | - $this->emitToken(array( |
|
| 979 | - 'name' => null, |
|
| 980 | - 'type' => self::DOCTYPE, |
|
| 981 | - 'error' => true |
|
| 982 | - )); |
|
| 983 | - |
|
| 984 | - $this->char--; |
|
| 985 | - $this->state = 'data'; |
|
| 986 | - |
|
| 987 | - } else { |
|
| 988 | - $this->token = array( |
|
| 989 | - 'name' => $char, |
|
| 990 | - 'type' => self::DOCTYPE, |
|
| 991 | - 'error' => true |
|
| 992 | - ); |
|
| 993 | - |
|
| 994 | - $this->state = 'doctypeName'; |
|
| 995 | - } |
|
| 996 | - } |
|
| 997 | - |
|
| 998 | - private function doctypeNameState() { |
|
| 999 | - /* Consume the next input character: */ |
|
| 1000 | - $this->char++; |
|
| 1001 | - $char = $this->char(); |
|
| 1002 | - |
|
| 1003 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1004 | - $this->state = 'AfterDoctypeName'; |
|
| 1005 | - |
|
| 1006 | - } elseif($char === '>') { |
|
| 1007 | - $this->emitToken($this->token); |
|
| 1008 | - $this->state = 'data'; |
|
| 1009 | - |
|
| 1010 | - } elseif(preg_match('/^[a-z]$/', $char)) { |
|
| 1011 | - $this->token['name'] .= strtoupper($char); |
|
| 1012 | - |
|
| 1013 | - } elseif($this->char === $this->EOF) { |
|
| 1014 | - $this->emitToken($this->token); |
|
| 1015 | - $this->char--; |
|
| 1016 | - $this->state = 'data'; |
|
| 1017 | - |
|
| 1018 | - } else { |
|
| 1019 | - $this->token['name'] .= $char; |
|
| 1020 | - } |
|
| 1021 | - |
|
| 1022 | - $this->token['error'] = ($this->token['name'] === 'HTML') |
|
| 1023 | - ? false |
|
| 1024 | - : true; |
|
| 1025 | - } |
|
| 1026 | - |
|
| 1027 | - private function afterDoctypeNameState() { |
|
| 1028 | - /* Consume the next input character: */ |
|
| 1029 | - $this->char++; |
|
| 1030 | - $char = $this->char(); |
|
| 1031 | - |
|
| 1032 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1033 | - // Stay in the DOCTYPE name state. |
|
| 1034 | - |
|
| 1035 | - } elseif($char === '>') { |
|
| 1036 | - $this->emitToken($this->token); |
|
| 1037 | - $this->state = 'data'; |
|
| 1038 | - |
|
| 1039 | - } elseif($this->char === $this->EOF) { |
|
| 1040 | - $this->emitToken($this->token); |
|
| 1041 | - $this->char--; |
|
| 1042 | - $this->state = 'data'; |
|
| 1043 | - |
|
| 1044 | - } else { |
|
| 1045 | - $this->token['error'] = true; |
|
| 1046 | - $this->state = 'bogusDoctype'; |
|
| 1047 | - } |
|
| 1048 | - } |
|
| 1049 | - |
|
| 1050 | - private function bogusDoctypeState() { |
|
| 1051 | - /* Consume the next input character: */ |
|
| 1052 | - $this->char++; |
|
| 1053 | - $char = $this->char(); |
|
| 1054 | - |
|
| 1055 | - if($char === '>') { |
|
| 1056 | - $this->emitToken($this->token); |
|
| 1057 | - $this->state = 'data'; |
|
| 1058 | - |
|
| 1059 | - } elseif($this->char === $this->EOF) { |
|
| 1060 | - $this->emitToken($this->token); |
|
| 1061 | - $this->char--; |
|
| 1062 | - $this->state = 'data'; |
|
| 1063 | - |
|
| 1064 | - } else { |
|
| 1065 | - // Stay in the bogus DOCTYPE state. |
|
| 1066 | - } |
|
| 1067 | - } |
|
| 1068 | - |
|
| 1069 | - private function entity() { |
|
| 1070 | - $start = $this->char; |
|
| 1071 | - |
|
| 1072 | - // This section defines how to consume an entity. This definition is |
|
| 1073 | - // used when parsing entities in text and in attributes. |
|
| 1074 | - |
|
| 1075 | - // The behaviour depends on the identity of the next character (the |
|
| 1076 | - // one immediately after the U+0026 AMPERSAND character): |
|
| 1077 | - |
|
| 1078 | - switch($this->character($this->char + 1)) { |
|
| 1079 | - // U+0023 NUMBER SIGN (#) |
|
| 1080 | - case '#': |
|
| 1081 | - |
|
| 1082 | - // The behaviour further depends on the character after the |
|
| 1083 | - // U+0023 NUMBER SIGN: |
|
| 1084 | - switch($this->character($this->char + 1)) { |
|
| 1085 | - // U+0078 LATIN SMALL LETTER X |
|
| 1086 | - // U+0058 LATIN CAPITAL LETTER X |
|
| 1087 | - case 'x': |
|
| 1088 | - case 'X': |
|
| 1089 | - // Follow the steps below, but using the range of |
|
| 1090 | - // characters U+0030 DIGIT ZERO through to U+0039 DIGIT |
|
| 1091 | - // NINE, U+0061 LATIN SMALL LETTER A through to U+0066 |
|
| 1092 | - // LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER |
|
| 1093 | - // A, through to U+0046 LATIN CAPITAL LETTER F (in other |
|
| 1094 | - // words, 0-9, A-F, a-f). |
|
| 1095 | - $char = 1; |
|
| 1096 | - $char_class = '0-9A-Fa-f'; |
|
| 1097 | - break; |
|
| 1098 | - |
|
| 1099 | - // Anything else |
|
| 1100 | - default: |
|
| 1101 | - // Follow the steps below, but using the range of |
|
| 1102 | - // characters U+0030 DIGIT ZERO through to U+0039 DIGIT |
|
| 1103 | - // NINE (i.e. just 0-9). |
|
| 1104 | - $char = 0; |
|
| 1105 | - $char_class = '0-9'; |
|
| 1106 | - break; |
|
| 1107 | - } |
|
| 1108 | - |
|
| 1109 | - // Consume as many characters as match the range of characters |
|
| 1110 | - // given above. |
|
| 1111 | - $this->char++; |
|
| 1112 | - $e_name = $this->characters($char_class, $this->char + $char + 1); |
|
| 1113 | - $entity = $this->character($start, $this->char); |
|
| 1114 | - $cond = strlen($e_name) > 0; |
|
| 1115 | - |
|
| 1116 | - // The rest of the parsing happens bellow. |
|
| 1117 | - break; |
|
| 1118 | - |
|
| 1119 | - // Anything else |
|
| 1120 | - default: |
|
| 1121 | - // Consume the maximum number of characters possible, with the |
|
| 1122 | - // consumed characters case-sensitively matching one of the |
|
| 1123 | - // identifiers in the first column of the entities table. |
|
| 1124 | - $e_name = $this->characters('0-9A-Za-z;', $this->char + 1); |
|
| 1125 | - $len = strlen($e_name); |
|
| 1126 | - |
|
| 1127 | - for($c = 1; $c <= $len; $c++) { |
|
| 1128 | - $id = substr($e_name, 0, $c); |
|
| 1129 | - $this->char++; |
|
| 1130 | - |
|
| 1131 | - if(in_array($id, $this->entities)) { |
|
| 1132 | - if ($e_name[$c-1] !== ';') { |
|
| 1133 | - if ($c < $len && $e_name[$c] == ';') { |
|
| 1134 | - $this->char++; // consume extra semicolon |
|
| 1135 | - } |
|
| 1136 | - } |
|
| 1137 | - $entity = $id; |
|
| 1138 | - break; |
|
| 1139 | - } |
|
| 1140 | - } |
|
| 1141 | - |
|
| 1142 | - $cond = isset($entity); |
|
| 1143 | - // The rest of the parsing happens bellow. |
|
| 1144 | - break; |
|
| 1145 | - } |
|
| 1146 | - |
|
| 1147 | - if(!$cond) { |
|
| 1148 | - // If no match can be made, then this is a parse error. No |
|
| 1149 | - // characters are consumed, and nothing is returned. |
|
| 1150 | - $this->char = $start; |
|
| 1151 | - return false; |
|
| 1152 | - } |
|
| 1153 | - |
|
| 1154 | - // Return a character token for the character corresponding to the |
|
| 1155 | - // entity name (as given by the second column of the entities table). |
|
| 1156 | - return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8'); |
|
| 1157 | - } |
|
| 1158 | - |
|
| 1159 | - private function emitToken($token) { |
|
| 1160 | - $emit = $this->tree->emitToken($token); |
|
| 1161 | - |
|
| 1162 | - if(is_int($emit)) { |
|
| 1163 | - $this->content_model = $emit; |
|
| 1164 | - |
|
| 1165 | - } elseif($token['type'] === self::ENDTAG) { |
|
| 1166 | - $this->content_model = self::PCDATA; |
|
| 1167 | - } |
|
| 1168 | - } |
|
| 1169 | - |
|
| 1170 | - private function EOF() { |
|
| 1171 | - $this->state = null; |
|
| 1172 | - $this->tree->emitToken(array( |
|
| 1173 | - 'type' => self::EOF |
|
| 1174 | - )); |
|
| 1175 | - } |
|
| 909 | + $this->token['data'] .= '-'.$char; |
|
| 910 | + $this->state = 'comment'; |
|
| 911 | + } |
|
| 912 | + } |
|
| 913 | + |
|
| 914 | + private function commentEndState() { |
|
| 915 | + /* Consume the next input character: */ |
|
| 916 | + $this->char++; |
|
| 917 | + $char = $this->char(); |
|
| 918 | + |
|
| 919 | + if($char === '>') { |
|
| 920 | + $this->emitToken($this->token); |
|
| 921 | + $this->state = 'data'; |
|
| 922 | + |
|
| 923 | + } elseif($char === '-') { |
|
| 924 | + $this->token['data'] .= '-'; |
|
| 925 | + |
|
| 926 | + } elseif($this->char === $this->EOF) { |
|
| 927 | + $this->emitToken($this->token); |
|
| 928 | + $this->char--; |
|
| 929 | + $this->state = 'data'; |
|
| 930 | + |
|
| 931 | + } else { |
|
| 932 | + $this->token['data'] .= '--'.$char; |
|
| 933 | + $this->state = 'comment'; |
|
| 934 | + } |
|
| 935 | + } |
|
| 936 | + |
|
| 937 | + private function doctypeState() { |
|
| 938 | + /* Consume the next input character: */ |
|
| 939 | + $this->char++; |
|
| 940 | + $char = $this->char(); |
|
| 941 | + |
|
| 942 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 943 | + $this->state = 'beforeDoctypeName'; |
|
| 944 | + |
|
| 945 | + } else { |
|
| 946 | + $this->char--; |
|
| 947 | + $this->state = 'beforeDoctypeName'; |
|
| 948 | + } |
|
| 949 | + } |
|
| 950 | + |
|
| 951 | + private function beforeDoctypeNameState() { |
|
| 952 | + /* Consume the next input character: */ |
|
| 953 | + $this->char++; |
|
| 954 | + $char = $this->char(); |
|
| 955 | + |
|
| 956 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 957 | + // Stay in the before DOCTYPE name state. |
|
| 958 | + |
|
| 959 | + } elseif(preg_match('/^[a-z]$/', $char)) { |
|
| 960 | + $this->token = array( |
|
| 961 | + 'name' => strtoupper($char), |
|
| 962 | + 'type' => self::DOCTYPE, |
|
| 963 | + 'error' => true |
|
| 964 | + ); |
|
| 965 | + |
|
| 966 | + $this->state = 'doctypeName'; |
|
| 967 | + |
|
| 968 | + } elseif($char === '>') { |
|
| 969 | + $this->emitToken(array( |
|
| 970 | + 'name' => null, |
|
| 971 | + 'type' => self::DOCTYPE, |
|
| 972 | + 'error' => true |
|
| 973 | + )); |
|
| 974 | + |
|
| 975 | + $this->state = 'data'; |
|
| 976 | + |
|
| 977 | + } elseif($this->char === $this->EOF) { |
|
| 978 | + $this->emitToken(array( |
|
| 979 | + 'name' => null, |
|
| 980 | + 'type' => self::DOCTYPE, |
|
| 981 | + 'error' => true |
|
| 982 | + )); |
|
| 983 | + |
|
| 984 | + $this->char--; |
|
| 985 | + $this->state = 'data'; |
|
| 986 | + |
|
| 987 | + } else { |
|
| 988 | + $this->token = array( |
|
| 989 | + 'name' => $char, |
|
| 990 | + 'type' => self::DOCTYPE, |
|
| 991 | + 'error' => true |
|
| 992 | + ); |
|
| 993 | + |
|
| 994 | + $this->state = 'doctypeName'; |
|
| 995 | + } |
|
| 996 | + } |
|
| 997 | + |
|
| 998 | + private function doctypeNameState() { |
|
| 999 | + /* Consume the next input character: */ |
|
| 1000 | + $this->char++; |
|
| 1001 | + $char = $this->char(); |
|
| 1002 | + |
|
| 1003 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1004 | + $this->state = 'AfterDoctypeName'; |
|
| 1005 | + |
|
| 1006 | + } elseif($char === '>') { |
|
| 1007 | + $this->emitToken($this->token); |
|
| 1008 | + $this->state = 'data'; |
|
| 1009 | + |
|
| 1010 | + } elseif(preg_match('/^[a-z]$/', $char)) { |
|
| 1011 | + $this->token['name'] .= strtoupper($char); |
|
| 1012 | + |
|
| 1013 | + } elseif($this->char === $this->EOF) { |
|
| 1014 | + $this->emitToken($this->token); |
|
| 1015 | + $this->char--; |
|
| 1016 | + $this->state = 'data'; |
|
| 1017 | + |
|
| 1018 | + } else { |
|
| 1019 | + $this->token['name'] .= $char; |
|
| 1020 | + } |
|
| 1021 | + |
|
| 1022 | + $this->token['error'] = ($this->token['name'] === 'HTML') |
|
| 1023 | + ? false |
|
| 1024 | + : true; |
|
| 1025 | + } |
|
| 1026 | + |
|
| 1027 | + private function afterDoctypeNameState() { |
|
| 1028 | + /* Consume the next input character: */ |
|
| 1029 | + $this->char++; |
|
| 1030 | + $char = $this->char(); |
|
| 1031 | + |
|
| 1032 | + if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1033 | + // Stay in the DOCTYPE name state. |
|
| 1034 | + |
|
| 1035 | + } elseif($char === '>') { |
|
| 1036 | + $this->emitToken($this->token); |
|
| 1037 | + $this->state = 'data'; |
|
| 1038 | + |
|
| 1039 | + } elseif($this->char === $this->EOF) { |
|
| 1040 | + $this->emitToken($this->token); |
|
| 1041 | + $this->char--; |
|
| 1042 | + $this->state = 'data'; |
|
| 1043 | + |
|
| 1044 | + } else { |
|
| 1045 | + $this->token['error'] = true; |
|
| 1046 | + $this->state = 'bogusDoctype'; |
|
| 1047 | + } |
|
| 1048 | + } |
|
| 1049 | + |
|
| 1050 | + private function bogusDoctypeState() { |
|
| 1051 | + /* Consume the next input character: */ |
|
| 1052 | + $this->char++; |
|
| 1053 | + $char = $this->char(); |
|
| 1054 | + |
|
| 1055 | + if($char === '>') { |
|
| 1056 | + $this->emitToken($this->token); |
|
| 1057 | + $this->state = 'data'; |
|
| 1058 | + |
|
| 1059 | + } elseif($this->char === $this->EOF) { |
|
| 1060 | + $this->emitToken($this->token); |
|
| 1061 | + $this->char--; |
|
| 1062 | + $this->state = 'data'; |
|
| 1063 | + |
|
| 1064 | + } else { |
|
| 1065 | + // Stay in the bogus DOCTYPE state. |
|
| 1066 | + } |
|
| 1067 | + } |
|
| 1068 | + |
|
| 1069 | + private function entity() { |
|
| 1070 | + $start = $this->char; |
|
| 1071 | + |
|
| 1072 | + // This section defines how to consume an entity. This definition is |
|
| 1073 | + // used when parsing entities in text and in attributes. |
|
| 1074 | + |
|
| 1075 | + // The behaviour depends on the identity of the next character (the |
|
| 1076 | + // one immediately after the U+0026 AMPERSAND character): |
|
| 1077 | + |
|
| 1078 | + switch($this->character($this->char + 1)) { |
|
| 1079 | + // U+0023 NUMBER SIGN (#) |
|
| 1080 | + case '#': |
|
| 1081 | + |
|
| 1082 | + // The behaviour further depends on the character after the |
|
| 1083 | + // U+0023 NUMBER SIGN: |
|
| 1084 | + switch($this->character($this->char + 1)) { |
|
| 1085 | + // U+0078 LATIN SMALL LETTER X |
|
| 1086 | + // U+0058 LATIN CAPITAL LETTER X |
|
| 1087 | + case 'x': |
|
| 1088 | + case 'X': |
|
| 1089 | + // Follow the steps below, but using the range of |
|
| 1090 | + // characters U+0030 DIGIT ZERO through to U+0039 DIGIT |
|
| 1091 | + // NINE, U+0061 LATIN SMALL LETTER A through to U+0066 |
|
| 1092 | + // LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER |
|
| 1093 | + // A, through to U+0046 LATIN CAPITAL LETTER F (in other |
|
| 1094 | + // words, 0-9, A-F, a-f). |
|
| 1095 | + $char = 1; |
|
| 1096 | + $char_class = '0-9A-Fa-f'; |
|
| 1097 | + break; |
|
| 1098 | + |
|
| 1099 | + // Anything else |
|
| 1100 | + default: |
|
| 1101 | + // Follow the steps below, but using the range of |
|
| 1102 | + // characters U+0030 DIGIT ZERO through to U+0039 DIGIT |
|
| 1103 | + // NINE (i.e. just 0-9). |
|
| 1104 | + $char = 0; |
|
| 1105 | + $char_class = '0-9'; |
|
| 1106 | + break; |
|
| 1107 | + } |
|
| 1108 | + |
|
| 1109 | + // Consume as many characters as match the range of characters |
|
| 1110 | + // given above. |
|
| 1111 | + $this->char++; |
|
| 1112 | + $e_name = $this->characters($char_class, $this->char + $char + 1); |
|
| 1113 | + $entity = $this->character($start, $this->char); |
|
| 1114 | + $cond = strlen($e_name) > 0; |
|
| 1115 | + |
|
| 1116 | + // The rest of the parsing happens bellow. |
|
| 1117 | + break; |
|
| 1118 | + |
|
| 1119 | + // Anything else |
|
| 1120 | + default: |
|
| 1121 | + // Consume the maximum number of characters possible, with the |
|
| 1122 | + // consumed characters case-sensitively matching one of the |
|
| 1123 | + // identifiers in the first column of the entities table. |
|
| 1124 | + $e_name = $this->characters('0-9A-Za-z;', $this->char + 1); |
|
| 1125 | + $len = strlen($e_name); |
|
| 1126 | + |
|
| 1127 | + for($c = 1; $c <= $len; $c++) { |
|
| 1128 | + $id = substr($e_name, 0, $c); |
|
| 1129 | + $this->char++; |
|
| 1130 | + |
|
| 1131 | + if(in_array($id, $this->entities)) { |
|
| 1132 | + if ($e_name[$c-1] !== ';') { |
|
| 1133 | + if ($c < $len && $e_name[$c] == ';') { |
|
| 1134 | + $this->char++; // consume extra semicolon |
|
| 1135 | + } |
|
| 1136 | + } |
|
| 1137 | + $entity = $id; |
|
| 1138 | + break; |
|
| 1139 | + } |
|
| 1140 | + } |
|
| 1141 | + |
|
| 1142 | + $cond = isset($entity); |
|
| 1143 | + // The rest of the parsing happens bellow. |
|
| 1144 | + break; |
|
| 1145 | + } |
|
| 1146 | + |
|
| 1147 | + if(!$cond) { |
|
| 1148 | + // If no match can be made, then this is a parse error. No |
|
| 1149 | + // characters are consumed, and nothing is returned. |
|
| 1150 | + $this->char = $start; |
|
| 1151 | + return false; |
|
| 1152 | + } |
|
| 1153 | + |
|
| 1154 | + // Return a character token for the character corresponding to the |
|
| 1155 | + // entity name (as given by the second column of the entities table). |
|
| 1156 | + return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8'); |
|
| 1157 | + } |
|
| 1158 | + |
|
| 1159 | + private function emitToken($token) { |
|
| 1160 | + $emit = $this->tree->emitToken($token); |
|
| 1161 | + |
|
| 1162 | + if(is_int($emit)) { |
|
| 1163 | + $this->content_model = $emit; |
|
| 1164 | + |
|
| 1165 | + } elseif($token['type'] === self::ENDTAG) { |
|
| 1166 | + $this->content_model = self::PCDATA; |
|
| 1167 | + } |
|
| 1168 | + } |
|
| 1169 | + |
|
| 1170 | + private function EOF() { |
|
| 1171 | + $this->state = null; |
|
| 1172 | + $this->tree->emitToken(array( |
|
| 1173 | + 'type' => self::EOF |
|
| 1174 | + )); |
|
| 1175 | + } |
|
| 1176 | 1176 | } |
| 1177 | 1177 | |
| 1178 | 1178 | class HTML5TreeConstructer { |
| 1179 | - public $stack = array(); |
|
| 1180 | - |
|
| 1181 | - private $phase; |
|
| 1182 | - private $mode; |
|
| 1183 | - private $dom; |
|
| 1184 | - private $foster_parent = null; |
|
| 1185 | - private $a_formatting = array(); |
|
| 1186 | - |
|
| 1187 | - private $head_pointer = null; |
|
| 1188 | - private $form_pointer = null; |
|
| 1189 | - |
|
| 1190 | - private $scoping = array('button','caption','html','marquee','object','table','td','th'); |
|
| 1191 | - private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u'); |
|
| 1192 | - private $special = array('address','area','base','basefont','bgsound', |
|
| 1193 | - 'blockquote','body','br','center','col','colgroup','dd','dir','div','dl', |
|
| 1194 | - 'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5', |
|
| 1195 | - 'h6','head','hr','iframe','image','img','input','isindex','li','link', |
|
| 1196 | - 'listing','menu','meta','noembed','noframes','noscript','ol','optgroup', |
|
| 1197 | - 'option','p','param','plaintext','pre','script','select','spacer','style', |
|
| 1198 | - 'tbody','textarea','tfoot','thead','title','tr','ul','wbr'); |
|
| 1199 | - |
|
| 1200 | - // The different phases. |
|
| 1201 | - const INIT_PHASE = 0; |
|
| 1202 | - const ROOT_PHASE = 1; |
|
| 1203 | - const MAIN_PHASE = 2; |
|
| 1204 | - const END_PHASE = 3; |
|
| 1205 | - |
|
| 1206 | - // The different insertion modes for the main phase. |
|
| 1207 | - const BEFOR_HEAD = 0; |
|
| 1208 | - const IN_HEAD = 1; |
|
| 1209 | - const AFTER_HEAD = 2; |
|
| 1210 | - const IN_BODY = 3; |
|
| 1211 | - const IN_TABLE = 4; |
|
| 1212 | - const IN_CAPTION = 5; |
|
| 1213 | - const IN_CGROUP = 6; |
|
| 1214 | - const IN_TBODY = 7; |
|
| 1215 | - const IN_ROW = 8; |
|
| 1216 | - const IN_CELL = 9; |
|
| 1217 | - const IN_SELECT = 10; |
|
| 1218 | - const AFTER_BODY = 11; |
|
| 1219 | - const IN_FRAME = 12; |
|
| 1220 | - const AFTR_FRAME = 13; |
|
| 1221 | - |
|
| 1222 | - // The different types of elements. |
|
| 1223 | - const SPECIAL = 0; |
|
| 1224 | - const SCOPING = 1; |
|
| 1225 | - const FORMATTING = 2; |
|
| 1226 | - const PHRASING = 3; |
|
| 1227 | - |
|
| 1228 | - const MARKER = 0; |
|
| 1229 | - |
|
| 1230 | - public function __construct() { |
|
| 1231 | - $this->phase = self::INIT_PHASE; |
|
| 1232 | - $this->mode = self::BEFOR_HEAD; |
|
| 1233 | - $this->dom = new DOMDocument; |
|
| 1234 | - |
|
| 1235 | - $this->dom->encoding = 'UTF-8'; |
|
| 1236 | - $this->dom->preserveWhiteSpace = true; |
|
| 1237 | - $this->dom->substituteEntities = true; |
|
| 1238 | - $this->dom->strictErrorChecking = false; |
|
| 1239 | - } |
|
| 1240 | - |
|
| 1241 | - // Process tag tokens |
|
| 1242 | - public function emitToken($token) { |
|
| 1243 | - switch($this->phase) { |
|
| 1244 | - case self::INIT_PHASE: return $this->initPhase($token); break; |
|
| 1245 | - case self::ROOT_PHASE: return $this->rootElementPhase($token); break; |
|
| 1246 | - case self::MAIN_PHASE: return $this->mainPhase($token); break; |
|
| 1247 | - case self::END_PHASE : return $this->trailingEndPhase($token); break; |
|
| 1248 | - } |
|
| 1249 | - } |
|
| 1250 | - |
|
| 1251 | - private function initPhase($token) { |
|
| 1252 | - /* Initially, the tree construction stage must handle each token |
|
| 1179 | + public $stack = array(); |
|
| 1180 | + |
|
| 1181 | + private $phase; |
|
| 1182 | + private $mode; |
|
| 1183 | + private $dom; |
|
| 1184 | + private $foster_parent = null; |
|
| 1185 | + private $a_formatting = array(); |
|
| 1186 | + |
|
| 1187 | + private $head_pointer = null; |
|
| 1188 | + private $form_pointer = null; |
|
| 1189 | + |
|
| 1190 | + private $scoping = array('button','caption','html','marquee','object','table','td','th'); |
|
| 1191 | + private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u'); |
|
| 1192 | + private $special = array('address','area','base','basefont','bgsound', |
|
| 1193 | + 'blockquote','body','br','center','col','colgroup','dd','dir','div','dl', |
|
| 1194 | + 'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5', |
|
| 1195 | + 'h6','head','hr','iframe','image','img','input','isindex','li','link', |
|
| 1196 | + 'listing','menu','meta','noembed','noframes','noscript','ol','optgroup', |
|
| 1197 | + 'option','p','param','plaintext','pre','script','select','spacer','style', |
|
| 1198 | + 'tbody','textarea','tfoot','thead','title','tr','ul','wbr'); |
|
| 1199 | + |
|
| 1200 | + // The different phases. |
|
| 1201 | + const INIT_PHASE = 0; |
|
| 1202 | + const ROOT_PHASE = 1; |
|
| 1203 | + const MAIN_PHASE = 2; |
|
| 1204 | + const END_PHASE = 3; |
|
| 1205 | + |
|
| 1206 | + // The different insertion modes for the main phase. |
|
| 1207 | + const BEFOR_HEAD = 0; |
|
| 1208 | + const IN_HEAD = 1; |
|
| 1209 | + const AFTER_HEAD = 2; |
|
| 1210 | + const IN_BODY = 3; |
|
| 1211 | + const IN_TABLE = 4; |
|
| 1212 | + const IN_CAPTION = 5; |
|
| 1213 | + const IN_CGROUP = 6; |
|
| 1214 | + const IN_TBODY = 7; |
|
| 1215 | + const IN_ROW = 8; |
|
| 1216 | + const IN_CELL = 9; |
|
| 1217 | + const IN_SELECT = 10; |
|
| 1218 | + const AFTER_BODY = 11; |
|
| 1219 | + const IN_FRAME = 12; |
|
| 1220 | + const AFTR_FRAME = 13; |
|
| 1221 | + |
|
| 1222 | + // The different types of elements. |
|
| 1223 | + const SPECIAL = 0; |
|
| 1224 | + const SCOPING = 1; |
|
| 1225 | + const FORMATTING = 2; |
|
| 1226 | + const PHRASING = 3; |
|
| 1227 | + |
|
| 1228 | + const MARKER = 0; |
|
| 1229 | + |
|
| 1230 | + public function __construct() { |
|
| 1231 | + $this->phase = self::INIT_PHASE; |
|
| 1232 | + $this->mode = self::BEFOR_HEAD; |
|
| 1233 | + $this->dom = new DOMDocument; |
|
| 1234 | + |
|
| 1235 | + $this->dom->encoding = 'UTF-8'; |
|
| 1236 | + $this->dom->preserveWhiteSpace = true; |
|
| 1237 | + $this->dom->substituteEntities = true; |
|
| 1238 | + $this->dom->strictErrorChecking = false; |
|
| 1239 | + } |
|
| 1240 | + |
|
| 1241 | + // Process tag tokens |
|
| 1242 | + public function emitToken($token) { |
|
| 1243 | + switch($this->phase) { |
|
| 1244 | + case self::INIT_PHASE: return $this->initPhase($token); break; |
|
| 1245 | + case self::ROOT_PHASE: return $this->rootElementPhase($token); break; |
|
| 1246 | + case self::MAIN_PHASE: return $this->mainPhase($token); break; |
|
| 1247 | + case self::END_PHASE : return $this->trailingEndPhase($token); break; |
|
| 1248 | + } |
|
| 1249 | + } |
|
| 1250 | + |
|
| 1251 | + private function initPhase($token) { |
|
| 1252 | + /* Initially, the tree construction stage must handle each token |
|
| 1253 | 1253 | emitted from the tokenisation stage as follows: */ |
| 1254 | 1254 | |
| 1255 | - /* A DOCTYPE token that is marked as being in error |
|
| 1255 | + /* A DOCTYPE token that is marked as being in error |
|
| 1256 | 1256 | A comment token |
| 1257 | 1257 | A start tag token |
| 1258 | 1258 | An end tag token |
@@ -1260,575 +1260,575 @@ discard block |
||
| 1260 | 1260 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1261 | 1261 | or U+0020 SPACE |
| 1262 | 1262 | An end-of-file token */ |
| 1263 | - if((isset($token['error']) && $token['error']) || |
|
| 1264 | - $token['type'] === HTML5::COMMENT || |
|
| 1265 | - $token['type'] === HTML5::STARTTAG || |
|
| 1266 | - $token['type'] === HTML5::ENDTAG || |
|
| 1267 | - $token['type'] === HTML5::EOF || |
|
| 1268 | - ($token['type'] === HTML5::CHARACTR && isset($token['data']) && |
|
| 1269 | - !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) { |
|
| 1270 | - /* This specification does not define how to handle this case. In |
|
| 1263 | + if((isset($token['error']) && $token['error']) || |
|
| 1264 | + $token['type'] === HTML5::COMMENT || |
|
| 1265 | + $token['type'] === HTML5::STARTTAG || |
|
| 1266 | + $token['type'] === HTML5::ENDTAG || |
|
| 1267 | + $token['type'] === HTML5::EOF || |
|
| 1268 | + ($token['type'] === HTML5::CHARACTR && isset($token['data']) && |
|
| 1269 | + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) { |
|
| 1270 | + /* This specification does not define how to handle this case. In |
|
| 1271 | 1271 | particular, user agents may ignore the entirety of this specification |
| 1272 | 1272 | altogether for such documents, and instead invoke special parse modes |
| 1273 | 1273 | with a greater emphasis on backwards compatibility. */ |
| 1274 | 1274 | |
| 1275 | - $this->phase = self::ROOT_PHASE; |
|
| 1276 | - return $this->rootElementPhase($token); |
|
| 1275 | + $this->phase = self::ROOT_PHASE; |
|
| 1276 | + return $this->rootElementPhase($token); |
|
| 1277 | 1277 | |
| 1278 | - /* A DOCTYPE token marked as being correct */ |
|
| 1279 | - } elseif(isset($token['error']) && !$token['error']) { |
|
| 1280 | - /* Append a DocumentType node to the Document node, with the name |
|
| 1278 | + /* A DOCTYPE token marked as being correct */ |
|
| 1279 | + } elseif(isset($token['error']) && !$token['error']) { |
|
| 1280 | + /* Append a DocumentType node to the Document node, with the name |
|
| 1281 | 1281 | attribute set to the name given in the DOCTYPE token (which will be |
| 1282 | 1282 | "HTML"), and the other attributes specific to DocumentType objects |
| 1283 | 1283 | set to null, empty lists, or the empty string as appropriate. */ |
| 1284 | - $doctype = new DOMDocumentType(null, null, 'HTML'); |
|
| 1284 | + $doctype = new DOMDocumentType(null, null, 'HTML'); |
|
| 1285 | 1285 | |
| 1286 | - /* Then, switch to the root element phase of the tree construction |
|
| 1286 | + /* Then, switch to the root element phase of the tree construction |
|
| 1287 | 1287 | stage. */ |
| 1288 | - $this->phase = self::ROOT_PHASE; |
|
| 1288 | + $this->phase = self::ROOT_PHASE; |
|
| 1289 | 1289 | |
| 1290 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1290 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1291 | 1291 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1292 | 1292 | or U+0020 SPACE */ |
| 1293 | - } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/', |
|
| 1294 | - $token['data'])) { |
|
| 1295 | - /* Append that character to the Document node. */ |
|
| 1296 | - $text = $this->dom->createTextNode($token['data']); |
|
| 1297 | - $this->dom->appendChild($text); |
|
| 1298 | - } |
|
| 1299 | - } |
|
| 1300 | - |
|
| 1301 | - private function rootElementPhase($token) { |
|
| 1302 | - /* After the initial phase, as each token is emitted from the tokenisation |
|
| 1293 | + } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/', |
|
| 1294 | + $token['data'])) { |
|
| 1295 | + /* Append that character to the Document node. */ |
|
| 1296 | + $text = $this->dom->createTextNode($token['data']); |
|
| 1297 | + $this->dom->appendChild($text); |
|
| 1298 | + } |
|
| 1299 | + } |
|
| 1300 | + |
|
| 1301 | + private function rootElementPhase($token) { |
|
| 1302 | + /* After the initial phase, as each token is emitted from the tokenisation |
|
| 1303 | 1303 | stage, it must be processed as described in this section. */ |
| 1304 | 1304 | |
| 1305 | - /* A DOCTYPE token */ |
|
| 1306 | - if($token['type'] === HTML5::DOCTYPE) { |
|
| 1307 | - // Parse error. Ignore the token. |
|
| 1305 | + /* A DOCTYPE token */ |
|
| 1306 | + if($token['type'] === HTML5::DOCTYPE) { |
|
| 1307 | + // Parse error. Ignore the token. |
|
| 1308 | 1308 | |
| 1309 | - /* A comment token */ |
|
| 1310 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1311 | - /* Append a Comment node to the Document object with the data |
|
| 1309 | + /* A comment token */ |
|
| 1310 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1311 | + /* Append a Comment node to the Document object with the data |
|
| 1312 | 1312 | attribute set to the data given in the comment token. */ |
| 1313 | - $comment = $this->dom->createComment($token['data']); |
|
| 1314 | - $this->dom->appendChild($comment); |
|
| 1313 | + $comment = $this->dom->createComment($token['data']); |
|
| 1314 | + $this->dom->appendChild($comment); |
|
| 1315 | 1315 | |
| 1316 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1316 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1317 | 1317 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1318 | 1318 | or U+0020 SPACE */ |
| 1319 | - } elseif($token['type'] === HTML5::CHARACTR && |
|
| 1320 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 1321 | - /* Append that character to the Document node. */ |
|
| 1322 | - $text = $this->dom->createTextNode($token['data']); |
|
| 1323 | - $this->dom->appendChild($text); |
|
| 1319 | + } elseif($token['type'] === HTML5::CHARACTR && |
|
| 1320 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 1321 | + /* Append that character to the Document node. */ |
|
| 1322 | + $text = $this->dom->createTextNode($token['data']); |
|
| 1323 | + $this->dom->appendChild($text); |
|
| 1324 | 1324 | |
| 1325 | - /* A character token that is not one of U+0009 CHARACTER TABULATION, |
|
| 1325 | + /* A character token that is not one of U+0009 CHARACTER TABULATION, |
|
| 1326 | 1326 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED |
| 1327 | 1327 | (FF), or U+0020 SPACE |
| 1328 | 1328 | A start tag token |
| 1329 | 1329 | An end tag token |
| 1330 | 1330 | An end-of-file token */ |
| 1331 | - } elseif(($token['type'] === HTML5::CHARACTR && |
|
| 1332 | - !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || |
|
| 1333 | - $token['type'] === HTML5::STARTTAG || |
|
| 1334 | - $token['type'] === HTML5::ENDTAG || |
|
| 1335 | - $token['type'] === HTML5::EOF) { |
|
| 1336 | - /* Create an HTMLElement node with the tag name html, in the HTML |
|
| 1331 | + } elseif(($token['type'] === HTML5::CHARACTR && |
|
| 1332 | + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || |
|
| 1333 | + $token['type'] === HTML5::STARTTAG || |
|
| 1334 | + $token['type'] === HTML5::ENDTAG || |
|
| 1335 | + $token['type'] === HTML5::EOF) { |
|
| 1336 | + /* Create an HTMLElement node with the tag name html, in the HTML |
|
| 1337 | 1337 | namespace. Append it to the Document object. Switch to the main |
| 1338 | 1338 | phase and reprocess the current token. */ |
| 1339 | - $html = $this->dom->createElement('html'); |
|
| 1340 | - $this->dom->appendChild($html); |
|
| 1341 | - $this->stack[] = $html; |
|
| 1339 | + $html = $this->dom->createElement('html'); |
|
| 1340 | + $this->dom->appendChild($html); |
|
| 1341 | + $this->stack[] = $html; |
|
| 1342 | 1342 | |
| 1343 | - $this->phase = self::MAIN_PHASE; |
|
| 1344 | - return $this->mainPhase($token); |
|
| 1345 | - } |
|
| 1346 | - } |
|
| 1343 | + $this->phase = self::MAIN_PHASE; |
|
| 1344 | + return $this->mainPhase($token); |
|
| 1345 | + } |
|
| 1346 | + } |
|
| 1347 | 1347 | |
| 1348 | - private function mainPhase($token) { |
|
| 1349 | - /* Tokens in the main phase must be handled as follows: */ |
|
| 1348 | + private function mainPhase($token) { |
|
| 1349 | + /* Tokens in the main phase must be handled as follows: */ |
|
| 1350 | 1350 | |
| 1351 | - /* A DOCTYPE token */ |
|
| 1352 | - if($token['type'] === HTML5::DOCTYPE) { |
|
| 1353 | - // Parse error. Ignore the token. |
|
| 1351 | + /* A DOCTYPE token */ |
|
| 1352 | + if($token['type'] === HTML5::DOCTYPE) { |
|
| 1353 | + // Parse error. Ignore the token. |
|
| 1354 | 1354 | |
| 1355 | - /* A start tag token with the tag name "html" */ |
|
| 1356 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { |
|
| 1357 | - /* If this start tag token was not the first start tag token, then |
|
| 1355 | + /* A start tag token with the tag name "html" */ |
|
| 1356 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { |
|
| 1357 | + /* If this start tag token was not the first start tag token, then |
|
| 1358 | 1358 | it is a parse error. */ |
| 1359 | 1359 | |
| 1360 | - /* For each attribute on the token, check to see if the attribute |
|
| 1360 | + /* For each attribute on the token, check to see if the attribute |
|
| 1361 | 1361 | is already present on the top element of the stack of open elements. |
| 1362 | 1362 | If it is not, add the attribute and its corresponding value to that |
| 1363 | 1363 | element. */ |
| 1364 | - foreach($token['attr'] as $attr) { |
|
| 1365 | - if(!$this->stack[0]->hasAttribute($attr['name'])) { |
|
| 1366 | - $this->stack[0]->setAttribute($attr['name'], $attr['value']); |
|
| 1367 | - } |
|
| 1368 | - } |
|
| 1369 | - |
|
| 1370 | - /* An end-of-file token */ |
|
| 1371 | - } elseif($token['type'] === HTML5::EOF) { |
|
| 1372 | - /* Generate implied end tags. */ |
|
| 1373 | - $this->generateImpliedEndTags(); |
|
| 1374 | - |
|
| 1375 | - /* Anything else. */ |
|
| 1376 | - } else { |
|
| 1377 | - /* Depends on the insertion mode: */ |
|
| 1378 | - switch($this->mode) { |
|
| 1379 | - case self::BEFOR_HEAD: return $this->beforeHead($token); break; |
|
| 1380 | - case self::IN_HEAD: return $this->inHead($token); break; |
|
| 1381 | - case self::AFTER_HEAD: return $this->afterHead($token); break; |
|
| 1382 | - case self::IN_BODY: return $this->inBody($token); break; |
|
| 1383 | - case self::IN_TABLE: return $this->inTable($token); break; |
|
| 1384 | - case self::IN_CAPTION: return $this->inCaption($token); break; |
|
| 1385 | - case self::IN_CGROUP: return $this->inColumnGroup($token); break; |
|
| 1386 | - case self::IN_TBODY: return $this->inTableBody($token); break; |
|
| 1387 | - case self::IN_ROW: return $this->inRow($token); break; |
|
| 1388 | - case self::IN_CELL: return $this->inCell($token); break; |
|
| 1389 | - case self::IN_SELECT: return $this->inSelect($token); break; |
|
| 1390 | - case self::AFTER_BODY: return $this->afterBody($token); break; |
|
| 1391 | - case self::IN_FRAME: return $this->inFrameset($token); break; |
|
| 1392 | - case self::AFTR_FRAME: return $this->afterFrameset($token); break; |
|
| 1393 | - case self::END_PHASE: return $this->trailingEndPhase($token); break; |
|
| 1394 | - } |
|
| 1395 | - } |
|
| 1396 | - } |
|
| 1397 | - |
|
| 1398 | - private function beforeHead($token) { |
|
| 1399 | - /* Handle the token as follows: */ |
|
| 1400 | - |
|
| 1401 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1364 | + foreach($token['attr'] as $attr) { |
|
| 1365 | + if(!$this->stack[0]->hasAttribute($attr['name'])) { |
|
| 1366 | + $this->stack[0]->setAttribute($attr['name'], $attr['value']); |
|
| 1367 | + } |
|
| 1368 | + } |
|
| 1369 | + |
|
| 1370 | + /* An end-of-file token */ |
|
| 1371 | + } elseif($token['type'] === HTML5::EOF) { |
|
| 1372 | + /* Generate implied end tags. */ |
|
| 1373 | + $this->generateImpliedEndTags(); |
|
| 1374 | + |
|
| 1375 | + /* Anything else. */ |
|
| 1376 | + } else { |
|
| 1377 | + /* Depends on the insertion mode: */ |
|
| 1378 | + switch($this->mode) { |
|
| 1379 | + case self::BEFOR_HEAD: return $this->beforeHead($token); break; |
|
| 1380 | + case self::IN_HEAD: return $this->inHead($token); break; |
|
| 1381 | + case self::AFTER_HEAD: return $this->afterHead($token); break; |
|
| 1382 | + case self::IN_BODY: return $this->inBody($token); break; |
|
| 1383 | + case self::IN_TABLE: return $this->inTable($token); break; |
|
| 1384 | + case self::IN_CAPTION: return $this->inCaption($token); break; |
|
| 1385 | + case self::IN_CGROUP: return $this->inColumnGroup($token); break; |
|
| 1386 | + case self::IN_TBODY: return $this->inTableBody($token); break; |
|
| 1387 | + case self::IN_ROW: return $this->inRow($token); break; |
|
| 1388 | + case self::IN_CELL: return $this->inCell($token); break; |
|
| 1389 | + case self::IN_SELECT: return $this->inSelect($token); break; |
|
| 1390 | + case self::AFTER_BODY: return $this->afterBody($token); break; |
|
| 1391 | + case self::IN_FRAME: return $this->inFrameset($token); break; |
|
| 1392 | + case self::AFTR_FRAME: return $this->afterFrameset($token); break; |
|
| 1393 | + case self::END_PHASE: return $this->trailingEndPhase($token); break; |
|
| 1394 | + } |
|
| 1395 | + } |
|
| 1396 | + } |
|
| 1397 | + |
|
| 1398 | + private function beforeHead($token) { |
|
| 1399 | + /* Handle the token as follows: */ |
|
| 1400 | + |
|
| 1401 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1402 | 1402 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1403 | 1403 | or U+0020 SPACE */ |
| 1404 | - if($token['type'] === HTML5::CHARACTR && |
|
| 1405 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 1406 | - /* Append the character to the current node. */ |
|
| 1407 | - $this->insertText($token['data']); |
|
| 1408 | - |
|
| 1409 | - /* A comment token */ |
|
| 1410 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1411 | - /* Append a Comment node to the current node with the data attribute |
|
| 1404 | + if($token['type'] === HTML5::CHARACTR && |
|
| 1405 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 1406 | + /* Append the character to the current node. */ |
|
| 1407 | + $this->insertText($token['data']); |
|
| 1408 | + |
|
| 1409 | + /* A comment token */ |
|
| 1410 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1411 | + /* Append a Comment node to the current node with the data attribute |
|
| 1412 | 1412 | set to the data given in the comment token. */ |
| 1413 | - $this->insertComment($token['data']); |
|
| 1413 | + $this->insertComment($token['data']); |
|
| 1414 | 1414 | |
| 1415 | - /* A start tag token with the tag name "head" */ |
|
| 1416 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') { |
|
| 1417 | - /* Create an element for the token, append the new element to the |
|
| 1415 | + /* A start tag token with the tag name "head" */ |
|
| 1416 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') { |
|
| 1417 | + /* Create an element for the token, append the new element to the |
|
| 1418 | 1418 | current node and push it onto the stack of open elements. */ |
| 1419 | - $element = $this->insertElement($token); |
|
| 1419 | + $element = $this->insertElement($token); |
|
| 1420 | 1420 | |
| 1421 | - /* Set the head element pointer to this new element node. */ |
|
| 1422 | - $this->head_pointer = $element; |
|
| 1421 | + /* Set the head element pointer to this new element node. */ |
|
| 1422 | + $this->head_pointer = $element; |
|
| 1423 | 1423 | |
| 1424 | - /* Change the insertion mode to "in head". */ |
|
| 1425 | - $this->mode = self::IN_HEAD; |
|
| 1424 | + /* Change the insertion mode to "in head". */ |
|
| 1425 | + $this->mode = self::IN_HEAD; |
|
| 1426 | 1426 | |
| 1427 | - /* A start tag token whose tag name is one of: "base", "link", "meta", |
|
| 1427 | + /* A start tag token whose tag name is one of: "base", "link", "meta", |
|
| 1428 | 1428 | "script", "style", "title". Or an end tag with the tag name "html". |
| 1429 | 1429 | Or a character token that is not one of U+0009 CHARACTER TABULATION, |
| 1430 | 1430 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1431 | 1431 | or U+0020 SPACE. Or any other start tag token */ |
| 1432 | - } elseif($token['type'] === HTML5::STARTTAG || |
|
| 1433 | - ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') || |
|
| 1434 | - ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/', |
|
| 1435 | - $token['data']))) { |
|
| 1436 | - /* Act as if a start tag token with the tag name "head" and no |
|
| 1432 | + } elseif($token['type'] === HTML5::STARTTAG || |
|
| 1433 | + ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') || |
|
| 1434 | + ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/', |
|
| 1435 | + $token['data']))) { |
|
| 1436 | + /* Act as if a start tag token with the tag name "head" and no |
|
| 1437 | 1437 | attributes had been seen, then reprocess the current token. */ |
| 1438 | - $this->beforeHead(array( |
|
| 1439 | - 'name' => 'head', |
|
| 1440 | - 'type' => HTML5::STARTTAG, |
|
| 1441 | - 'attr' => array() |
|
| 1442 | - )); |
|
| 1438 | + $this->beforeHead(array( |
|
| 1439 | + 'name' => 'head', |
|
| 1440 | + 'type' => HTML5::STARTTAG, |
|
| 1441 | + 'attr' => array() |
|
| 1442 | + )); |
|
| 1443 | 1443 | |
| 1444 | - return $this->inHead($token); |
|
| 1444 | + return $this->inHead($token); |
|
| 1445 | 1445 | |
| 1446 | - /* Any other end tag */ |
|
| 1447 | - } elseif($token['type'] === HTML5::ENDTAG) { |
|
| 1448 | - /* Parse error. Ignore the token. */ |
|
| 1449 | - } |
|
| 1450 | - } |
|
| 1446 | + /* Any other end tag */ |
|
| 1447 | + } elseif($token['type'] === HTML5::ENDTAG) { |
|
| 1448 | + /* Parse error. Ignore the token. */ |
|
| 1449 | + } |
|
| 1450 | + } |
|
| 1451 | 1451 | |
| 1452 | - private function inHead($token) { |
|
| 1453 | - /* Handle the token as follows: */ |
|
| 1452 | + private function inHead($token) { |
|
| 1453 | + /* Handle the token as follows: */ |
|
| 1454 | 1454 | |
| 1455 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1455 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1456 | 1456 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1457 | 1457 | or U+0020 SPACE. |
| 1458 | 1458 | |
| 1459 | 1459 | THIS DIFFERS FROM THE SPEC: If the current node is either a title, style |
| 1460 | 1460 | or script element, append the character to the current node regardless |
| 1461 | 1461 | of its content. */ |
| 1462 | - if(($token['type'] === HTML5::CHARACTR && |
|
| 1463 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || ( |
|
| 1464 | - $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName, |
|
| 1465 | - array('title', 'style', 'script')))) { |
|
| 1466 | - /* Append the character to the current node. */ |
|
| 1467 | - $this->insertText($token['data']); |
|
| 1468 | - |
|
| 1469 | - /* A comment token */ |
|
| 1470 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1471 | - /* Append a Comment node to the current node with the data attribute |
|
| 1462 | + if(($token['type'] === HTML5::CHARACTR && |
|
| 1463 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || ( |
|
| 1464 | + $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName, |
|
| 1465 | + array('title', 'style', 'script')))) { |
|
| 1466 | + /* Append the character to the current node. */ |
|
| 1467 | + $this->insertText($token['data']); |
|
| 1468 | + |
|
| 1469 | + /* A comment token */ |
|
| 1470 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1471 | + /* Append a Comment node to the current node with the data attribute |
|
| 1472 | 1472 | set to the data given in the comment token. */ |
| 1473 | - $this->insertComment($token['data']); |
|
| 1473 | + $this->insertComment($token['data']); |
|
| 1474 | 1474 | |
| 1475 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 1476 | - in_array($token['name'], array('title', 'style', 'script'))) { |
|
| 1477 | - array_pop($this->stack); |
|
| 1478 | - return HTML5::PCDATA; |
|
| 1475 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 1476 | + in_array($token['name'], array('title', 'style', 'script'))) { |
|
| 1477 | + array_pop($this->stack); |
|
| 1478 | + return HTML5::PCDATA; |
|
| 1479 | 1479 | |
| 1480 | - /* A start tag with the tag name "title" */ |
|
| 1481 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') { |
|
| 1482 | - /* Create an element for the token and append the new element to the |
|
| 1480 | + /* A start tag with the tag name "title" */ |
|
| 1481 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') { |
|
| 1482 | + /* Create an element for the token and append the new element to the |
|
| 1483 | 1483 | node pointed to by the head element pointer, or, if that is null |
| 1484 | 1484 | (innerHTML case), to the current node. */ |
| 1485 | - if($this->head_pointer !== null) { |
|
| 1486 | - $element = $this->insertElement($token, false); |
|
| 1487 | - $this->head_pointer->appendChild($element); |
|
| 1485 | + if($this->head_pointer !== null) { |
|
| 1486 | + $element = $this->insertElement($token, false); |
|
| 1487 | + $this->head_pointer->appendChild($element); |
|
| 1488 | 1488 | |
| 1489 | - } else { |
|
| 1490 | - $element = $this->insertElement($token); |
|
| 1491 | - } |
|
| 1489 | + } else { |
|
| 1490 | + $element = $this->insertElement($token); |
|
| 1491 | + } |
|
| 1492 | 1492 | |
| 1493 | - /* Switch the tokeniser's content model flag to the RCDATA state. */ |
|
| 1494 | - return HTML5::RCDATA; |
|
| 1493 | + /* Switch the tokeniser's content model flag to the RCDATA state. */ |
|
| 1494 | + return HTML5::RCDATA; |
|
| 1495 | 1495 | |
| 1496 | - /* A start tag with the tag name "style" */ |
|
| 1497 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') { |
|
| 1498 | - /* Create an element for the token and append the new element to the |
|
| 1496 | + /* A start tag with the tag name "style" */ |
|
| 1497 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') { |
|
| 1498 | + /* Create an element for the token and append the new element to the |
|
| 1499 | 1499 | node pointed to by the head element pointer, or, if that is null |
| 1500 | 1500 | (innerHTML case), to the current node. */ |
| 1501 | - if($this->head_pointer !== null) { |
|
| 1502 | - $element = $this->insertElement($token, false); |
|
| 1503 | - $this->head_pointer->appendChild($element); |
|
| 1504 | - |
|
| 1505 | - } else { |
|
| 1506 | - $this->insertElement($token); |
|
| 1507 | - } |
|
| 1508 | - |
|
| 1509 | - /* Switch the tokeniser's content model flag to the CDATA state. */ |
|
| 1510 | - return HTML5::CDATA; |
|
| 1511 | - |
|
| 1512 | - /* A start tag with the tag name "script" */ |
|
| 1513 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { |
|
| 1514 | - /* Create an element for the token. */ |
|
| 1515 | - $element = $this->insertElement($token, false); |
|
| 1516 | - $this->head_pointer->appendChild($element); |
|
| 1517 | - |
|
| 1518 | - /* Switch the tokeniser's content model flag to the CDATA state. */ |
|
| 1519 | - return HTML5::CDATA; |
|
| 1520 | - |
|
| 1521 | - /* A start tag with the tag name "base", "link", or "meta" */ |
|
| 1522 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1523 | - array('base', 'link', 'meta'))) { |
|
| 1524 | - /* Create an element for the token and append the new element to the |
|
| 1501 | + if($this->head_pointer !== null) { |
|
| 1502 | + $element = $this->insertElement($token, false); |
|
| 1503 | + $this->head_pointer->appendChild($element); |
|
| 1504 | + |
|
| 1505 | + } else { |
|
| 1506 | + $this->insertElement($token); |
|
| 1507 | + } |
|
| 1508 | + |
|
| 1509 | + /* Switch the tokeniser's content model flag to the CDATA state. */ |
|
| 1510 | + return HTML5::CDATA; |
|
| 1511 | + |
|
| 1512 | + /* A start tag with the tag name "script" */ |
|
| 1513 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { |
|
| 1514 | + /* Create an element for the token. */ |
|
| 1515 | + $element = $this->insertElement($token, false); |
|
| 1516 | + $this->head_pointer->appendChild($element); |
|
| 1517 | + |
|
| 1518 | + /* Switch the tokeniser's content model flag to the CDATA state. */ |
|
| 1519 | + return HTML5::CDATA; |
|
| 1520 | + |
|
| 1521 | + /* A start tag with the tag name "base", "link", or "meta" */ |
|
| 1522 | + } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1523 | + array('base', 'link', 'meta'))) { |
|
| 1524 | + /* Create an element for the token and append the new element to the |
|
| 1525 | 1525 | node pointed to by the head element pointer, or, if that is null |
| 1526 | 1526 | (innerHTML case), to the current node. */ |
| 1527 | - if($this->head_pointer !== null) { |
|
| 1528 | - $element = $this->insertElement($token, false); |
|
| 1529 | - $this->head_pointer->appendChild($element); |
|
| 1530 | - array_pop($this->stack); |
|
| 1531 | - |
|
| 1532 | - } else { |
|
| 1533 | - $this->insertElement($token); |
|
| 1534 | - } |
|
| 1535 | - |
|
| 1536 | - /* An end tag with the tag name "head" */ |
|
| 1537 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { |
|
| 1538 | - /* If the current node is a head element, pop the current node off |
|
| 1527 | + if($this->head_pointer !== null) { |
|
| 1528 | + $element = $this->insertElement($token, false); |
|
| 1529 | + $this->head_pointer->appendChild($element); |
|
| 1530 | + array_pop($this->stack); |
|
| 1531 | + |
|
| 1532 | + } else { |
|
| 1533 | + $this->insertElement($token); |
|
| 1534 | + } |
|
| 1535 | + |
|
| 1536 | + /* An end tag with the tag name "head" */ |
|
| 1537 | + } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { |
|
| 1538 | + /* If the current node is a head element, pop the current node off |
|
| 1539 | 1539 | the stack of open elements. */ |
| 1540 | - if($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1541 | - array_pop($this->stack); |
|
| 1540 | + if($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1541 | + array_pop($this->stack); |
|
| 1542 | 1542 | |
| 1543 | - /* Otherwise, this is a parse error. */ |
|
| 1544 | - } else { |
|
| 1545 | - // k |
|
| 1546 | - } |
|
| 1543 | + /* Otherwise, this is a parse error. */ |
|
| 1544 | + } else { |
|
| 1545 | + // k |
|
| 1546 | + } |
|
| 1547 | 1547 | |
| 1548 | - /* Change the insertion mode to "after head". */ |
|
| 1549 | - $this->mode = self::AFTER_HEAD; |
|
| 1548 | + /* Change the insertion mode to "after head". */ |
|
| 1549 | + $this->mode = self::AFTER_HEAD; |
|
| 1550 | 1550 | |
| 1551 | - /* A start tag with the tag name "head" or an end tag except "html". */ |
|
| 1552 | - } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || |
|
| 1553 | - ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) { |
|
| 1554 | - // Parse error. Ignore the token. |
|
| 1551 | + /* A start tag with the tag name "head" or an end tag except "html". */ |
|
| 1552 | + } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || |
|
| 1553 | + ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) { |
|
| 1554 | + // Parse error. Ignore the token. |
|
| 1555 | 1555 | |
| 1556 | - /* Anything else */ |
|
| 1557 | - } else { |
|
| 1558 | - /* If the current node is a head element, act as if an end tag |
|
| 1556 | + /* Anything else */ |
|
| 1557 | + } else { |
|
| 1558 | + /* If the current node is a head element, act as if an end tag |
|
| 1559 | 1559 | token with the tag name "head" had been seen. */ |
| 1560 | - if($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1561 | - $this->inHead(array( |
|
| 1562 | - 'name' => 'head', |
|
| 1563 | - 'type' => HTML5::ENDTAG |
|
| 1564 | - )); |
|
| 1565 | - |
|
| 1566 | - /* Otherwise, change the insertion mode to "after head". */ |
|
| 1567 | - } else { |
|
| 1568 | - $this->mode = self::AFTER_HEAD; |
|
| 1569 | - } |
|
| 1570 | - |
|
| 1571 | - /* Then, reprocess the current token. */ |
|
| 1572 | - return $this->afterHead($token); |
|
| 1573 | - } |
|
| 1574 | - } |
|
| 1575 | - |
|
| 1576 | - private function afterHead($token) { |
|
| 1577 | - /* Handle the token as follows: */ |
|
| 1578 | - |
|
| 1579 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1560 | + if($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1561 | + $this->inHead(array( |
|
| 1562 | + 'name' => 'head', |
|
| 1563 | + 'type' => HTML5::ENDTAG |
|
| 1564 | + )); |
|
| 1565 | + |
|
| 1566 | + /* Otherwise, change the insertion mode to "after head". */ |
|
| 1567 | + } else { |
|
| 1568 | + $this->mode = self::AFTER_HEAD; |
|
| 1569 | + } |
|
| 1570 | + |
|
| 1571 | + /* Then, reprocess the current token. */ |
|
| 1572 | + return $this->afterHead($token); |
|
| 1573 | + } |
|
| 1574 | + } |
|
| 1575 | + |
|
| 1576 | + private function afterHead($token) { |
|
| 1577 | + /* Handle the token as follows: */ |
|
| 1578 | + |
|
| 1579 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 1580 | 1580 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1581 | 1581 | or U+0020 SPACE */ |
| 1582 | - if($token['type'] === HTML5::CHARACTR && |
|
| 1583 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 1584 | - /* Append the character to the current node. */ |
|
| 1585 | - $this->insertText($token['data']); |
|
| 1586 | - |
|
| 1587 | - /* A comment token */ |
|
| 1588 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1589 | - /* Append a Comment node to the current node with the data attribute |
|
| 1582 | + if($token['type'] === HTML5::CHARACTR && |
|
| 1583 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 1584 | + /* Append the character to the current node. */ |
|
| 1585 | + $this->insertText($token['data']); |
|
| 1586 | + |
|
| 1587 | + /* A comment token */ |
|
| 1588 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1589 | + /* Append a Comment node to the current node with the data attribute |
|
| 1590 | 1590 | set to the data given in the comment token. */ |
| 1591 | - $this->insertComment($token['data']); |
|
| 1591 | + $this->insertComment($token['data']); |
|
| 1592 | 1592 | |
| 1593 | - /* A start tag token with the tag name "body" */ |
|
| 1594 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') { |
|
| 1595 | - /* Insert a body element for the token. */ |
|
| 1596 | - $this->insertElement($token); |
|
| 1593 | + /* A start tag token with the tag name "body" */ |
|
| 1594 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') { |
|
| 1595 | + /* Insert a body element for the token. */ |
|
| 1596 | + $this->insertElement($token); |
|
| 1597 | 1597 | |
| 1598 | - /* Change the insertion mode to "in body". */ |
|
| 1599 | - $this->mode = self::IN_BODY; |
|
| 1598 | + /* Change the insertion mode to "in body". */ |
|
| 1599 | + $this->mode = self::IN_BODY; |
|
| 1600 | 1600 | |
| 1601 | - /* A start tag token with the tag name "frameset" */ |
|
| 1602 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') { |
|
| 1603 | - /* Insert a frameset element for the token. */ |
|
| 1604 | - $this->insertElement($token); |
|
| 1601 | + /* A start tag token with the tag name "frameset" */ |
|
| 1602 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') { |
|
| 1603 | + /* Insert a frameset element for the token. */ |
|
| 1604 | + $this->insertElement($token); |
|
| 1605 | 1605 | |
| 1606 | - /* Change the insertion mode to "in frameset". */ |
|
| 1607 | - $this->mode = self::IN_FRAME; |
|
| 1606 | + /* Change the insertion mode to "in frameset". */ |
|
| 1607 | + $this->mode = self::IN_FRAME; |
|
| 1608 | 1608 | |
| 1609 | - /* A start tag token whose tag name is one of: "base", "link", "meta", |
|
| 1609 | + /* A start tag token whose tag name is one of: "base", "link", "meta", |
|
| 1610 | 1610 | "script", "style", "title" */ |
| 1611 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1612 | - array('base', 'link', 'meta', 'script', 'style', 'title'))) { |
|
| 1613 | - /* Parse error. Switch the insertion mode back to "in head" and |
|
| 1611 | + } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1612 | + array('base', 'link', 'meta', 'script', 'style', 'title'))) { |
|
| 1613 | + /* Parse error. Switch the insertion mode back to "in head" and |
|
| 1614 | 1614 | reprocess the token. */ |
| 1615 | - $this->mode = self::IN_HEAD; |
|
| 1616 | - return $this->inHead($token); |
|
| 1615 | + $this->mode = self::IN_HEAD; |
|
| 1616 | + return $this->inHead($token); |
|
| 1617 | 1617 | |
| 1618 | - /* Anything else */ |
|
| 1619 | - } else { |
|
| 1620 | - /* Act as if a start tag token with the tag name "body" and no |
|
| 1618 | + /* Anything else */ |
|
| 1619 | + } else { |
|
| 1620 | + /* Act as if a start tag token with the tag name "body" and no |
|
| 1621 | 1621 | attributes had been seen, and then reprocess the current token. */ |
| 1622 | - $this->afterHead(array( |
|
| 1623 | - 'name' => 'body', |
|
| 1624 | - 'type' => HTML5::STARTTAG, |
|
| 1625 | - 'attr' => array() |
|
| 1626 | - )); |
|
| 1627 | - |
|
| 1628 | - return $this->inBody($token); |
|
| 1629 | - } |
|
| 1630 | - } |
|
| 1631 | - |
|
| 1632 | - private function inBody($token) { |
|
| 1633 | - /* Handle the token as follows: */ |
|
| 1634 | - |
|
| 1635 | - switch($token['type']) { |
|
| 1636 | - /* A character token */ |
|
| 1637 | - case HTML5::CHARACTR: |
|
| 1638 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1639 | - $this->reconstructActiveFormattingElements(); |
|
| 1640 | - |
|
| 1641 | - /* Append the token's character to the current node. */ |
|
| 1642 | - $this->insertText($token['data']); |
|
| 1643 | - break; |
|
| 1644 | - |
|
| 1645 | - /* A comment token */ |
|
| 1646 | - case HTML5::COMMENT: |
|
| 1647 | - /* Append a Comment node to the current node with the data |
|
| 1622 | + $this->afterHead(array( |
|
| 1623 | + 'name' => 'body', |
|
| 1624 | + 'type' => HTML5::STARTTAG, |
|
| 1625 | + 'attr' => array() |
|
| 1626 | + )); |
|
| 1627 | + |
|
| 1628 | + return $this->inBody($token); |
|
| 1629 | + } |
|
| 1630 | + } |
|
| 1631 | + |
|
| 1632 | + private function inBody($token) { |
|
| 1633 | + /* Handle the token as follows: */ |
|
| 1634 | + |
|
| 1635 | + switch($token['type']) { |
|
| 1636 | + /* A character token */ |
|
| 1637 | + case HTML5::CHARACTR: |
|
| 1638 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1639 | + $this->reconstructActiveFormattingElements(); |
|
| 1640 | + |
|
| 1641 | + /* Append the token's character to the current node. */ |
|
| 1642 | + $this->insertText($token['data']); |
|
| 1643 | + break; |
|
| 1644 | + |
|
| 1645 | + /* A comment token */ |
|
| 1646 | + case HTML5::COMMENT: |
|
| 1647 | + /* Append a Comment node to the current node with the data |
|
| 1648 | 1648 | attribute set to the data given in the comment token. */ |
| 1649 | - $this->insertComment($token['data']); |
|
| 1650 | - break; |
|
| 1649 | + $this->insertComment($token['data']); |
|
| 1650 | + break; |
|
| 1651 | 1651 | |
| 1652 | - case HTML5::STARTTAG: |
|
| 1653 | - switch($token['name']) { |
|
| 1654 | - /* A start tag token whose tag name is one of: "script", |
|
| 1652 | + case HTML5::STARTTAG: |
|
| 1653 | + switch($token['name']) { |
|
| 1654 | + /* A start tag token whose tag name is one of: "script", |
|
| 1655 | 1655 | "style" */ |
| 1656 | - case 'script': case 'style': |
|
| 1657 | - /* Process the token as if the insertion mode had been "in |
|
| 1656 | + case 'script': case 'style': |
|
| 1657 | + /* Process the token as if the insertion mode had been "in |
|
| 1658 | 1658 | head". */ |
| 1659 | - return $this->inHead($token); |
|
| 1660 | - break; |
|
| 1659 | + return $this->inHead($token); |
|
| 1660 | + break; |
|
| 1661 | 1661 | |
| 1662 | - /* A start tag token whose tag name is one of: "base", "link", |
|
| 1662 | + /* A start tag token whose tag name is one of: "base", "link", |
|
| 1663 | 1663 | "meta", "title" */ |
| 1664 | - case 'base': case 'link': case 'meta': case 'title': |
|
| 1665 | - /* Parse error. Process the token as if the insertion mode |
|
| 1664 | + case 'base': case 'link': case 'meta': case 'title': |
|
| 1665 | + /* Parse error. Process the token as if the insertion mode |
|
| 1666 | 1666 | had been "in head". */ |
| 1667 | - return $this->inHead($token); |
|
| 1668 | - break; |
|
| 1667 | + return $this->inHead($token); |
|
| 1668 | + break; |
|
| 1669 | 1669 | |
| 1670 | - /* A start tag token with the tag name "body" */ |
|
| 1671 | - case 'body': |
|
| 1672 | - /* Parse error. If the second element on the stack of open |
|
| 1670 | + /* A start tag token with the tag name "body" */ |
|
| 1671 | + case 'body': |
|
| 1672 | + /* Parse error. If the second element on the stack of open |
|
| 1673 | 1673 | elements is not a body element, or, if the stack of open |
| 1674 | 1674 | elements has only one node on it, then ignore the token. |
| 1675 | 1675 | (innerHTML case) */ |
| 1676 | - if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') { |
|
| 1677 | - // Ignore |
|
| 1676 | + if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') { |
|
| 1677 | + // Ignore |
|
| 1678 | 1678 | |
| 1679 | - /* Otherwise, for each attribute on the token, check to see |
|
| 1679 | + /* Otherwise, for each attribute on the token, check to see |
|
| 1680 | 1680 | if the attribute is already present on the body element (the |
| 1681 | 1681 | second element) on the stack of open elements. If it is not, |
| 1682 | 1682 | add the attribute and its corresponding value to that |
| 1683 | 1683 | element. */ |
| 1684 | - } else { |
|
| 1685 | - foreach($token['attr'] as $attr) { |
|
| 1686 | - if(!$this->stack[1]->hasAttribute($attr['name'])) { |
|
| 1687 | - $this->stack[1]->setAttribute($attr['name'], $attr['value']); |
|
| 1688 | - } |
|
| 1689 | - } |
|
| 1690 | - } |
|
| 1691 | - break; |
|
| 1692 | - |
|
| 1693 | - /* A start tag whose tag name is one of: "address", |
|
| 1684 | + } else { |
|
| 1685 | + foreach($token['attr'] as $attr) { |
|
| 1686 | + if(!$this->stack[1]->hasAttribute($attr['name'])) { |
|
| 1687 | + $this->stack[1]->setAttribute($attr['name'], $attr['value']); |
|
| 1688 | + } |
|
| 1689 | + } |
|
| 1690 | + } |
|
| 1691 | + break; |
|
| 1692 | + |
|
| 1693 | + /* A start tag whose tag name is one of: "address", |
|
| 1694 | 1694 | "blockquote", "center", "dir", "div", "dl", "fieldset", |
| 1695 | 1695 | "listing", "menu", "ol", "p", "ul" */ |
| 1696 | - case 'address': case 'blockquote': case 'center': case 'dir': |
|
| 1697 | - case 'div': case 'dl': case 'fieldset': case 'listing': |
|
| 1698 | - case 'menu': case 'ol': case 'p': case 'ul': |
|
| 1699 | - /* If the stack of open elements has a p element in scope, |
|
| 1696 | + case 'address': case 'blockquote': case 'center': case 'dir': |
|
| 1697 | + case 'div': case 'dl': case 'fieldset': case 'listing': |
|
| 1698 | + case 'menu': case 'ol': case 'p': case 'ul': |
|
| 1699 | + /* If the stack of open elements has a p element in scope, |
|
| 1700 | 1700 | then act as if an end tag with the tag name p had been |
| 1701 | 1701 | seen. */ |
| 1702 | - if($this->elementInScope('p')) { |
|
| 1703 | - $this->emitToken(array( |
|
| 1704 | - 'name' => 'p', |
|
| 1705 | - 'type' => HTML5::ENDTAG |
|
| 1706 | - )); |
|
| 1707 | - } |
|
| 1708 | - |
|
| 1709 | - /* Insert an HTML element for the token. */ |
|
| 1710 | - $this->insertElement($token); |
|
| 1711 | - break; |
|
| 1712 | - |
|
| 1713 | - /* A start tag whose tag name is "form" */ |
|
| 1714 | - case 'form': |
|
| 1715 | - /* If the form element pointer is not null, ignore the |
|
| 1702 | + if($this->elementInScope('p')) { |
|
| 1703 | + $this->emitToken(array( |
|
| 1704 | + 'name' => 'p', |
|
| 1705 | + 'type' => HTML5::ENDTAG |
|
| 1706 | + )); |
|
| 1707 | + } |
|
| 1708 | + |
|
| 1709 | + /* Insert an HTML element for the token. */ |
|
| 1710 | + $this->insertElement($token); |
|
| 1711 | + break; |
|
| 1712 | + |
|
| 1713 | + /* A start tag whose tag name is "form" */ |
|
| 1714 | + case 'form': |
|
| 1715 | + /* If the form element pointer is not null, ignore the |
|
| 1716 | 1716 | token with a parse error. */ |
| 1717 | - if($this->form_pointer !== null) { |
|
| 1718 | - // Ignore. |
|
| 1717 | + if($this->form_pointer !== null) { |
|
| 1718 | + // Ignore. |
|
| 1719 | 1719 | |
| 1720 | - /* Otherwise: */ |
|
| 1721 | - } else { |
|
| 1722 | - /* If the stack of open elements has a p element in |
|
| 1720 | + /* Otherwise: */ |
|
| 1721 | + } else { |
|
| 1722 | + /* If the stack of open elements has a p element in |
|
| 1723 | 1723 | scope, then act as if an end tag with the tag name p |
| 1724 | 1724 | had been seen. */ |
| 1725 | - if($this->elementInScope('p')) { |
|
| 1726 | - $this->emitToken(array( |
|
| 1727 | - 'name' => 'p', |
|
| 1728 | - 'type' => HTML5::ENDTAG |
|
| 1729 | - )); |
|
| 1730 | - } |
|
| 1731 | - |
|
| 1732 | - /* Insert an HTML element for the token, and set the |
|
| 1725 | + if($this->elementInScope('p')) { |
|
| 1726 | + $this->emitToken(array( |
|
| 1727 | + 'name' => 'p', |
|
| 1728 | + 'type' => HTML5::ENDTAG |
|
| 1729 | + )); |
|
| 1730 | + } |
|
| 1731 | + |
|
| 1732 | + /* Insert an HTML element for the token, and set the |
|
| 1733 | 1733 | form element pointer to point to the element created. */ |
| 1734 | - $element = $this->insertElement($token); |
|
| 1735 | - $this->form_pointer = $element; |
|
| 1736 | - } |
|
| 1737 | - break; |
|
| 1738 | - |
|
| 1739 | - /* A start tag whose tag name is "li", "dd" or "dt" */ |
|
| 1740 | - case 'li': case 'dd': case 'dt': |
|
| 1741 | - /* If the stack of open elements has a p element in scope, |
|
| 1734 | + $element = $this->insertElement($token); |
|
| 1735 | + $this->form_pointer = $element; |
|
| 1736 | + } |
|
| 1737 | + break; |
|
| 1738 | + |
|
| 1739 | + /* A start tag whose tag name is "li", "dd" or "dt" */ |
|
| 1740 | + case 'li': case 'dd': case 'dt': |
|
| 1741 | + /* If the stack of open elements has a p element in scope, |
|
| 1742 | 1742 | then act as if an end tag with the tag name p had been |
| 1743 | 1743 | seen. */ |
| 1744 | - if($this->elementInScope('p')) { |
|
| 1745 | - $this->emitToken(array( |
|
| 1746 | - 'name' => 'p', |
|
| 1747 | - 'type' => HTML5::ENDTAG |
|
| 1748 | - )); |
|
| 1749 | - } |
|
| 1744 | + if($this->elementInScope('p')) { |
|
| 1745 | + $this->emitToken(array( |
|
| 1746 | + 'name' => 'p', |
|
| 1747 | + 'type' => HTML5::ENDTAG |
|
| 1748 | + )); |
|
| 1749 | + } |
|
| 1750 | 1750 | |
| 1751 | - $stack_length = count($this->stack) - 1; |
|
| 1751 | + $stack_length = count($this->stack) - 1; |
|
| 1752 | 1752 | |
| 1753 | - for($n = $stack_length; 0 <= $n; $n--) { |
|
| 1754 | - /* 1. Initialise node to be the current node (the |
|
| 1753 | + for($n = $stack_length; 0 <= $n; $n--) { |
|
| 1754 | + /* 1. Initialise node to be the current node (the |
|
| 1755 | 1755 | bottommost node of the stack). */ |
| 1756 | - $stop = false; |
|
| 1757 | - $node = $this->stack[$n]; |
|
| 1758 | - $cat = $this->getElementCategory($node->tagName); |
|
| 1756 | + $stop = false; |
|
| 1757 | + $node = $this->stack[$n]; |
|
| 1758 | + $cat = $this->getElementCategory($node->tagName); |
|
| 1759 | 1759 | |
| 1760 | - /* 2. If node is an li, dd or dt element, then pop all |
|
| 1760 | + /* 2. If node is an li, dd or dt element, then pop all |
|
| 1761 | 1761 | the nodes from the current node up to node, including |
| 1762 | 1762 | node, then stop this algorithm. */ |
| 1763 | - if($token['name'] === $node->tagName || ($token['name'] !== 'li' |
|
| 1764 | - && ($node->tagName === 'dd' || $node->tagName === 'dt'))) { |
|
| 1765 | - for($x = $stack_length; $x >= $n ; $x--) { |
|
| 1766 | - array_pop($this->stack); |
|
| 1767 | - } |
|
| 1763 | + if($token['name'] === $node->tagName || ($token['name'] !== 'li' |
|
| 1764 | + && ($node->tagName === 'dd' || $node->tagName === 'dt'))) { |
|
| 1765 | + for($x = $stack_length; $x >= $n ; $x--) { |
|
| 1766 | + array_pop($this->stack); |
|
| 1767 | + } |
|
| 1768 | 1768 | |
| 1769 | - break; |
|
| 1770 | - } |
|
| 1769 | + break; |
|
| 1770 | + } |
|
| 1771 | 1771 | |
| 1772 | - /* 3. If node is not in the formatting category, and is |
|
| 1772 | + /* 3. If node is not in the formatting category, and is |
|
| 1773 | 1773 | not in the phrasing category, and is not an address or |
| 1774 | 1774 | div element, then stop this algorithm. */ |
| 1775 | - if($cat !== self::FORMATTING && $cat !== self::PHRASING && |
|
| 1776 | - $node->tagName !== 'address' && $node->tagName !== 'div') { |
|
| 1777 | - break; |
|
| 1778 | - } |
|
| 1779 | - } |
|
| 1775 | + if($cat !== self::FORMATTING && $cat !== self::PHRASING && |
|
| 1776 | + $node->tagName !== 'address' && $node->tagName !== 'div') { |
|
| 1777 | + break; |
|
| 1778 | + } |
|
| 1779 | + } |
|
| 1780 | 1780 | |
| 1781 | - /* Finally, insert an HTML element with the same tag |
|
| 1781 | + /* Finally, insert an HTML element with the same tag |
|
| 1782 | 1782 | name as the token's. */ |
| 1783 | - $this->insertElement($token); |
|
| 1784 | - break; |
|
| 1783 | + $this->insertElement($token); |
|
| 1784 | + break; |
|
| 1785 | 1785 | |
| 1786 | - /* A start tag token whose tag name is "plaintext" */ |
|
| 1787 | - case 'plaintext': |
|
| 1788 | - /* If the stack of open elements has a p element in scope, |
|
| 1786 | + /* A start tag token whose tag name is "plaintext" */ |
|
| 1787 | + case 'plaintext': |
|
| 1788 | + /* If the stack of open elements has a p element in scope, |
|
| 1789 | 1789 | then act as if an end tag with the tag name p had been |
| 1790 | 1790 | seen. */ |
| 1791 | - if($this->elementInScope('p')) { |
|
| 1792 | - $this->emitToken(array( |
|
| 1793 | - 'name' => 'p', |
|
| 1794 | - 'type' => HTML5::ENDTAG |
|
| 1795 | - )); |
|
| 1796 | - } |
|
| 1791 | + if($this->elementInScope('p')) { |
|
| 1792 | + $this->emitToken(array( |
|
| 1793 | + 'name' => 'p', |
|
| 1794 | + 'type' => HTML5::ENDTAG |
|
| 1795 | + )); |
|
| 1796 | + } |
|
| 1797 | 1797 | |
| 1798 | - /* Insert an HTML element for the token. */ |
|
| 1799 | - $this->insertElement($token); |
|
| 1798 | + /* Insert an HTML element for the token. */ |
|
| 1799 | + $this->insertElement($token); |
|
| 1800 | 1800 | |
| 1801 | - return HTML5::PLAINTEXT; |
|
| 1802 | - break; |
|
| 1801 | + return HTML5::PLAINTEXT; |
|
| 1802 | + break; |
|
| 1803 | 1803 | |
| 1804 | - /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4", |
|
| 1804 | + /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4", |
|
| 1805 | 1805 | "h5", "h6" */ |
| 1806 | - case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6': |
|
| 1807 | - /* If the stack of open elements has a p element in scope, |
|
| 1806 | + case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6': |
|
| 1807 | + /* If the stack of open elements has a p element in scope, |
|
| 1808 | 1808 | then act as if an end tag with the tag name p had been seen. */ |
| 1809 | - if($this->elementInScope('p')) { |
|
| 1810 | - $this->emitToken(array( |
|
| 1811 | - 'name' => 'p', |
|
| 1812 | - 'type' => HTML5::ENDTAG |
|
| 1813 | - )); |
|
| 1814 | - } |
|
| 1815 | - |
|
| 1816 | - /* If the stack of open elements has in scope an element whose |
|
| 1809 | + if($this->elementInScope('p')) { |
|
| 1810 | + $this->emitToken(array( |
|
| 1811 | + 'name' => 'p', |
|
| 1812 | + 'type' => HTML5::ENDTAG |
|
| 1813 | + )); |
|
| 1814 | + } |
|
| 1815 | + |
|
| 1816 | + /* If the stack of open elements has in scope an element whose |
|
| 1817 | 1817 | tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then |
| 1818 | 1818 | this is a parse error; pop elements from the stack until an |
| 1819 | 1819 | element with one of those tag names has been popped from the |
| 1820 | 1820 | stack. */ |
| 1821 | - while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { |
|
| 1822 | - array_pop($this->stack); |
|
| 1823 | - } |
|
| 1821 | + while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { |
|
| 1822 | + array_pop($this->stack); |
|
| 1823 | + } |
|
| 1824 | 1824 | |
| 1825 | - /* Insert an HTML element for the token. */ |
|
| 1826 | - $this->insertElement($token); |
|
| 1827 | - break; |
|
| 1825 | + /* Insert an HTML element for the token. */ |
|
| 1826 | + $this->insertElement($token); |
|
| 1827 | + break; |
|
| 1828 | 1828 | |
| 1829 | - /* A start tag whose tag name is "a" */ |
|
| 1830 | - case 'a': |
|
| 1831 | - /* If the list of active formatting elements contains |
|
| 1829 | + /* A start tag whose tag name is "a" */ |
|
| 1830 | + case 'a': |
|
| 1831 | + /* If the list of active formatting elements contains |
|
| 1832 | 1832 | an element whose tag name is "a" between the end of the |
| 1833 | 1833 | list and the last marker on the list (or the start of |
| 1834 | 1834 | the list if there is no marker on the list), then this |
@@ -1837,940 +1837,940 @@ discard block |
||
| 1837 | 1837 | of active formatting elements and the stack of open |
| 1838 | 1838 | elements if the end tag didn't already remove it (it |
| 1839 | 1839 | might not have if the element is not in table scope). */ |
| 1840 | - $leng = count($this->a_formatting); |
|
| 1840 | + $leng = count($this->a_formatting); |
|
| 1841 | 1841 | |
| 1842 | - for($n = $leng - 1; $n >= 0; $n--) { |
|
| 1843 | - if($this->a_formatting[$n] === self::MARKER) { |
|
| 1844 | - break; |
|
| 1842 | + for($n = $leng - 1; $n >= 0; $n--) { |
|
| 1843 | + if($this->a_formatting[$n] === self::MARKER) { |
|
| 1844 | + break; |
|
| 1845 | 1845 | |
| 1846 | - } elseif($this->a_formatting[$n]->nodeName === 'a') { |
|
| 1847 | - $this->emitToken(array( |
|
| 1848 | - 'name' => 'a', |
|
| 1849 | - 'type' => HTML5::ENDTAG |
|
| 1850 | - )); |
|
| 1851 | - break; |
|
| 1852 | - } |
|
| 1853 | - } |
|
| 1846 | + } elseif($this->a_formatting[$n]->nodeName === 'a') { |
|
| 1847 | + $this->emitToken(array( |
|
| 1848 | + 'name' => 'a', |
|
| 1849 | + 'type' => HTML5::ENDTAG |
|
| 1850 | + )); |
|
| 1851 | + break; |
|
| 1852 | + } |
|
| 1853 | + } |
|
| 1854 | 1854 | |
| 1855 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1856 | - $this->reconstructActiveFormattingElements(); |
|
| 1855 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1856 | + $this->reconstructActiveFormattingElements(); |
|
| 1857 | 1857 | |
| 1858 | - /* Insert an HTML element for the token. */ |
|
| 1859 | - $el = $this->insertElement($token); |
|
| 1858 | + /* Insert an HTML element for the token. */ |
|
| 1859 | + $el = $this->insertElement($token); |
|
| 1860 | 1860 | |
| 1861 | - /* Add that element to the list of active formatting |
|
| 1861 | + /* Add that element to the list of active formatting |
|
| 1862 | 1862 | elements. */ |
| 1863 | - $this->a_formatting[] = $el; |
|
| 1864 | - break; |
|
| 1863 | + $this->a_formatting[] = $el; |
|
| 1864 | + break; |
|
| 1865 | 1865 | |
| 1866 | - /* A start tag whose tag name is one of: "b", "big", "em", "font", |
|
| 1866 | + /* A start tag whose tag name is one of: "b", "big", "em", "font", |
|
| 1867 | 1867 | "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ |
| 1868 | - case 'b': case 'big': case 'em': case 'font': case 'i': |
|
| 1869 | - case 'nobr': case 's': case 'small': case 'strike': |
|
| 1870 | - case 'strong': case 'tt': case 'u': |
|
| 1871 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1872 | - $this->reconstructActiveFormattingElements(); |
|
| 1868 | + case 'b': case 'big': case 'em': case 'font': case 'i': |
|
| 1869 | + case 'nobr': case 's': case 'small': case 'strike': |
|
| 1870 | + case 'strong': case 'tt': case 'u': |
|
| 1871 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1872 | + $this->reconstructActiveFormattingElements(); |
|
| 1873 | 1873 | |
| 1874 | - /* Insert an HTML element for the token. */ |
|
| 1875 | - $el = $this->insertElement($token); |
|
| 1874 | + /* Insert an HTML element for the token. */ |
|
| 1875 | + $el = $this->insertElement($token); |
|
| 1876 | 1876 | |
| 1877 | - /* Add that element to the list of active formatting |
|
| 1877 | + /* Add that element to the list of active formatting |
|
| 1878 | 1878 | elements. */ |
| 1879 | - $this->a_formatting[] = $el; |
|
| 1880 | - break; |
|
| 1879 | + $this->a_formatting[] = $el; |
|
| 1880 | + break; |
|
| 1881 | 1881 | |
| 1882 | - /* A start tag token whose tag name is "button" */ |
|
| 1883 | - case 'button': |
|
| 1884 | - /* If the stack of open elements has a button element in scope, |
|
| 1882 | + /* A start tag token whose tag name is "button" */ |
|
| 1883 | + case 'button': |
|
| 1884 | + /* If the stack of open elements has a button element in scope, |
|
| 1885 | 1885 | then this is a parse error; act as if an end tag with the tag |
| 1886 | 1886 | name "button" had been seen, then reprocess the token. (We don't |
| 1887 | 1887 | do that. Unnecessary.) */ |
| 1888 | - if($this->elementInScope('button')) { |
|
| 1889 | - $this->inBody(array( |
|
| 1890 | - 'name' => 'button', |
|
| 1891 | - 'type' => HTML5::ENDTAG |
|
| 1892 | - )); |
|
| 1893 | - } |
|
| 1888 | + if($this->elementInScope('button')) { |
|
| 1889 | + $this->inBody(array( |
|
| 1890 | + 'name' => 'button', |
|
| 1891 | + 'type' => HTML5::ENDTAG |
|
| 1892 | + )); |
|
| 1893 | + } |
|
| 1894 | 1894 | |
| 1895 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1896 | - $this->reconstructActiveFormattingElements(); |
|
| 1895 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1896 | + $this->reconstructActiveFormattingElements(); |
|
| 1897 | 1897 | |
| 1898 | - /* Insert an HTML element for the token. */ |
|
| 1899 | - $this->insertElement($token); |
|
| 1898 | + /* Insert an HTML element for the token. */ |
|
| 1899 | + $this->insertElement($token); |
|
| 1900 | 1900 | |
| 1901 | - /* Insert a marker at the end of the list of active |
|
| 1901 | + /* Insert a marker at the end of the list of active |
|
| 1902 | 1902 | formatting elements. */ |
| 1903 | - $this->a_formatting[] = self::MARKER; |
|
| 1904 | - break; |
|
| 1903 | + $this->a_formatting[] = self::MARKER; |
|
| 1904 | + break; |
|
| 1905 | 1905 | |
| 1906 | - /* A start tag token whose tag name is one of: "marquee", "object" */ |
|
| 1907 | - case 'marquee': case 'object': |
|
| 1908 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1909 | - $this->reconstructActiveFormattingElements(); |
|
| 1906 | + /* A start tag token whose tag name is one of: "marquee", "object" */ |
|
| 1907 | + case 'marquee': case 'object': |
|
| 1908 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1909 | + $this->reconstructActiveFormattingElements(); |
|
| 1910 | 1910 | |
| 1911 | - /* Insert an HTML element for the token. */ |
|
| 1912 | - $this->insertElement($token); |
|
| 1911 | + /* Insert an HTML element for the token. */ |
|
| 1912 | + $this->insertElement($token); |
|
| 1913 | 1913 | |
| 1914 | - /* Insert a marker at the end of the list of active |
|
| 1914 | + /* Insert a marker at the end of the list of active |
|
| 1915 | 1915 | formatting elements. */ |
| 1916 | - $this->a_formatting[] = self::MARKER; |
|
| 1917 | - break; |
|
| 1916 | + $this->a_formatting[] = self::MARKER; |
|
| 1917 | + break; |
|
| 1918 | 1918 | |
| 1919 | - /* A start tag token whose tag name is "xmp" */ |
|
| 1920 | - case 'xmp': |
|
| 1921 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1922 | - $this->reconstructActiveFormattingElements(); |
|
| 1919 | + /* A start tag token whose tag name is "xmp" */ |
|
| 1920 | + case 'xmp': |
|
| 1921 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1922 | + $this->reconstructActiveFormattingElements(); |
|
| 1923 | 1923 | |
| 1924 | - /* Insert an HTML element for the token. */ |
|
| 1925 | - $this->insertElement($token); |
|
| 1924 | + /* Insert an HTML element for the token. */ |
|
| 1925 | + $this->insertElement($token); |
|
| 1926 | 1926 | |
| 1927 | - /* Switch the content model flag to the CDATA state. */ |
|
| 1928 | - return HTML5::CDATA; |
|
| 1929 | - break; |
|
| 1927 | + /* Switch the content model flag to the CDATA state. */ |
|
| 1928 | + return HTML5::CDATA; |
|
| 1929 | + break; |
|
| 1930 | 1930 | |
| 1931 | - /* A start tag whose tag name is "table" */ |
|
| 1932 | - case 'table': |
|
| 1933 | - /* If the stack of open elements has a p element in scope, |
|
| 1931 | + /* A start tag whose tag name is "table" */ |
|
| 1932 | + case 'table': |
|
| 1933 | + /* If the stack of open elements has a p element in scope, |
|
| 1934 | 1934 | then act as if an end tag with the tag name p had been seen. */ |
| 1935 | - if($this->elementInScope('p')) { |
|
| 1936 | - $this->emitToken(array( |
|
| 1937 | - 'name' => 'p', |
|
| 1938 | - 'type' => HTML5::ENDTAG |
|
| 1939 | - )); |
|
| 1940 | - } |
|
| 1935 | + if($this->elementInScope('p')) { |
|
| 1936 | + $this->emitToken(array( |
|
| 1937 | + 'name' => 'p', |
|
| 1938 | + 'type' => HTML5::ENDTAG |
|
| 1939 | + )); |
|
| 1940 | + } |
|
| 1941 | 1941 | |
| 1942 | - /* Insert an HTML element for the token. */ |
|
| 1943 | - $this->insertElement($token); |
|
| 1942 | + /* Insert an HTML element for the token. */ |
|
| 1943 | + $this->insertElement($token); |
|
| 1944 | 1944 | |
| 1945 | - /* Change the insertion mode to "in table". */ |
|
| 1946 | - $this->mode = self::IN_TABLE; |
|
| 1947 | - break; |
|
| 1945 | + /* Change the insertion mode to "in table". */ |
|
| 1946 | + $this->mode = self::IN_TABLE; |
|
| 1947 | + break; |
|
| 1948 | 1948 | |
| 1949 | - /* A start tag whose tag name is one of: "area", "basefont", |
|
| 1949 | + /* A start tag whose tag name is one of: "area", "basefont", |
|
| 1950 | 1950 | "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */ |
| 1951 | - case 'area': case 'basefont': case 'bgsound': case 'br': |
|
| 1952 | - case 'embed': case 'img': case 'param': case 'spacer': |
|
| 1953 | - case 'wbr': |
|
| 1954 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1955 | - $this->reconstructActiveFormattingElements(); |
|
| 1956 | - |
|
| 1957 | - /* Insert an HTML element for the token. */ |
|
| 1958 | - $this->insertElement($token); |
|
| 1959 | - |
|
| 1960 | - /* Immediately pop the current node off the stack of open elements. */ |
|
| 1961 | - array_pop($this->stack); |
|
| 1962 | - break; |
|
| 1963 | - |
|
| 1964 | - /* A start tag whose tag name is "hr" */ |
|
| 1965 | - case 'hr': |
|
| 1966 | - /* If the stack of open elements has a p element in scope, |
|
| 1951 | + case 'area': case 'basefont': case 'bgsound': case 'br': |
|
| 1952 | + case 'embed': case 'img': case 'param': case 'spacer': |
|
| 1953 | + case 'wbr': |
|
| 1954 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1955 | + $this->reconstructActiveFormattingElements(); |
|
| 1956 | + |
|
| 1957 | + /* Insert an HTML element for the token. */ |
|
| 1958 | + $this->insertElement($token); |
|
| 1959 | + |
|
| 1960 | + /* Immediately pop the current node off the stack of open elements. */ |
|
| 1961 | + array_pop($this->stack); |
|
| 1962 | + break; |
|
| 1963 | + |
|
| 1964 | + /* A start tag whose tag name is "hr" */ |
|
| 1965 | + case 'hr': |
|
| 1966 | + /* If the stack of open elements has a p element in scope, |
|
| 1967 | 1967 | then act as if an end tag with the tag name p had been seen. */ |
| 1968 | - if($this->elementInScope('p')) { |
|
| 1969 | - $this->emitToken(array( |
|
| 1970 | - 'name' => 'p', |
|
| 1971 | - 'type' => HTML5::ENDTAG |
|
| 1972 | - )); |
|
| 1973 | - } |
|
| 1974 | - |
|
| 1975 | - /* Insert an HTML element for the token. */ |
|
| 1976 | - $this->insertElement($token); |
|
| 1977 | - |
|
| 1978 | - /* Immediately pop the current node off the stack of open elements. */ |
|
| 1979 | - array_pop($this->stack); |
|
| 1980 | - break; |
|
| 1981 | - |
|
| 1982 | - /* A start tag whose tag name is "image" */ |
|
| 1983 | - case 'image': |
|
| 1984 | - /* Parse error. Change the token's tag name to "img" and |
|
| 1968 | + if($this->elementInScope('p')) { |
|
| 1969 | + $this->emitToken(array( |
|
| 1970 | + 'name' => 'p', |
|
| 1971 | + 'type' => HTML5::ENDTAG |
|
| 1972 | + )); |
|
| 1973 | + } |
|
| 1974 | + |
|
| 1975 | + /* Insert an HTML element for the token. */ |
|
| 1976 | + $this->insertElement($token); |
|
| 1977 | + |
|
| 1978 | + /* Immediately pop the current node off the stack of open elements. */ |
|
| 1979 | + array_pop($this->stack); |
|
| 1980 | + break; |
|
| 1981 | + |
|
| 1982 | + /* A start tag whose tag name is "image" */ |
|
| 1983 | + case 'image': |
|
| 1984 | + /* Parse error. Change the token's tag name to "img" and |
|
| 1985 | 1985 | reprocess it. (Don't ask.) */ |
| 1986 | - $token['name'] = 'img'; |
|
| 1987 | - return $this->inBody($token); |
|
| 1988 | - break; |
|
| 1986 | + $token['name'] = 'img'; |
|
| 1987 | + return $this->inBody($token); |
|
| 1988 | + break; |
|
| 1989 | 1989 | |
| 1990 | - /* A start tag whose tag name is "input" */ |
|
| 1991 | - case 'input': |
|
| 1992 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 1993 | - $this->reconstructActiveFormattingElements(); |
|
| 1990 | + /* A start tag whose tag name is "input" */ |
|
| 1991 | + case 'input': |
|
| 1992 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 1993 | + $this->reconstructActiveFormattingElements(); |
|
| 1994 | 1994 | |
| 1995 | - /* Insert an input element for the token. */ |
|
| 1996 | - $element = $this->insertElement($token, false); |
|
| 1995 | + /* Insert an input element for the token. */ |
|
| 1996 | + $element = $this->insertElement($token, false); |
|
| 1997 | 1997 | |
| 1998 | - /* If the form element pointer is not null, then associate the |
|
| 1998 | + /* If the form element pointer is not null, then associate the |
|
| 1999 | 1999 | input element with the form element pointed to by the form |
| 2000 | 2000 | element pointer. */ |
| 2001 | - $this->form_pointer !== null |
|
| 2002 | - ? $this->form_pointer->appendChild($element) |
|
| 2003 | - : end($this->stack)->appendChild($element); |
|
| 2001 | + $this->form_pointer !== null |
|
| 2002 | + ? $this->form_pointer->appendChild($element) |
|
| 2003 | + : end($this->stack)->appendChild($element); |
|
| 2004 | 2004 | |
| 2005 | - /* Pop that input element off the stack of open elements. */ |
|
| 2006 | - array_pop($this->stack); |
|
| 2007 | - break; |
|
| 2005 | + /* Pop that input element off the stack of open elements. */ |
|
| 2006 | + array_pop($this->stack); |
|
| 2007 | + break; |
|
| 2008 | 2008 | |
| 2009 | - /* A start tag whose tag name is "isindex" */ |
|
| 2010 | - case 'isindex': |
|
| 2011 | - /* Parse error. */ |
|
| 2012 | - // w/e |
|
| 2009 | + /* A start tag whose tag name is "isindex" */ |
|
| 2010 | + case 'isindex': |
|
| 2011 | + /* Parse error. */ |
|
| 2012 | + // w/e |
|
| 2013 | 2013 | |
| 2014 | - /* If the form element pointer is not null, |
|
| 2014 | + /* If the form element pointer is not null, |
|
| 2015 | 2015 | then ignore the token. */ |
| 2016 | - if($this->form_pointer === null) { |
|
| 2017 | - /* Act as if a start tag token with the tag name "form" had |
|
| 2016 | + if($this->form_pointer === null) { |
|
| 2017 | + /* Act as if a start tag token with the tag name "form" had |
|
| 2018 | 2018 | been seen. */ |
| 2019 | - $this->inBody(array( |
|
| 2020 | - 'name' => 'body', |
|
| 2021 | - 'type' => HTML5::STARTTAG, |
|
| 2022 | - 'attr' => array() |
|
| 2023 | - )); |
|
| 2019 | + $this->inBody(array( |
|
| 2020 | + 'name' => 'body', |
|
| 2021 | + 'type' => HTML5::STARTTAG, |
|
| 2022 | + 'attr' => array() |
|
| 2023 | + )); |
|
| 2024 | 2024 | |
| 2025 | - /* Act as if a start tag token with the tag name "hr" had |
|
| 2025 | + /* Act as if a start tag token with the tag name "hr" had |
|
| 2026 | 2026 | been seen. */ |
| 2027 | - $this->inBody(array( |
|
| 2028 | - 'name' => 'hr', |
|
| 2029 | - 'type' => HTML5::STARTTAG, |
|
| 2030 | - 'attr' => array() |
|
| 2031 | - )); |
|
| 2027 | + $this->inBody(array( |
|
| 2028 | + 'name' => 'hr', |
|
| 2029 | + 'type' => HTML5::STARTTAG, |
|
| 2030 | + 'attr' => array() |
|
| 2031 | + )); |
|
| 2032 | 2032 | |
| 2033 | - /* Act as if a start tag token with the tag name "p" had |
|
| 2033 | + /* Act as if a start tag token with the tag name "p" had |
|
| 2034 | 2034 | been seen. */ |
| 2035 | - $this->inBody(array( |
|
| 2036 | - 'name' => 'p', |
|
| 2037 | - 'type' => HTML5::STARTTAG, |
|
| 2038 | - 'attr' => array() |
|
| 2039 | - )); |
|
| 2035 | + $this->inBody(array( |
|
| 2036 | + 'name' => 'p', |
|
| 2037 | + 'type' => HTML5::STARTTAG, |
|
| 2038 | + 'attr' => array() |
|
| 2039 | + )); |
|
| 2040 | 2040 | |
| 2041 | - /* Act as if a start tag token with the tag name "label" |
|
| 2041 | + /* Act as if a start tag token with the tag name "label" |
|
| 2042 | 2042 | had been seen. */ |
| 2043 | - $this->inBody(array( |
|
| 2044 | - 'name' => 'label', |
|
| 2045 | - 'type' => HTML5::STARTTAG, |
|
| 2046 | - 'attr' => array() |
|
| 2047 | - )); |
|
| 2043 | + $this->inBody(array( |
|
| 2044 | + 'name' => 'label', |
|
| 2045 | + 'type' => HTML5::STARTTAG, |
|
| 2046 | + 'attr' => array() |
|
| 2047 | + )); |
|
| 2048 | 2048 | |
| 2049 | - /* Act as if a stream of character tokens had been seen. */ |
|
| 2050 | - $this->insertText('This is a searchable index. '. |
|
| 2051 | - 'Insert your search keywords here: '); |
|
| 2049 | + /* Act as if a stream of character tokens had been seen. */ |
|
| 2050 | + $this->insertText('This is a searchable index. '. |
|
| 2051 | + 'Insert your search keywords here: '); |
|
| 2052 | 2052 | |
| 2053 | - /* Act as if a start tag token with the tag name "input" |
|
| 2053 | + /* Act as if a start tag token with the tag name "input" |
|
| 2054 | 2054 | had been seen, with all the attributes from the "isindex" |
| 2055 | 2055 | token, except with the "name" attribute set to the value |
| 2056 | 2056 | "isindex" (ignoring any explicit "name" attribute). */ |
| 2057 | - $attr = $token['attr']; |
|
| 2058 | - $attr[] = array('name' => 'name', 'value' => 'isindex'); |
|
| 2057 | + $attr = $token['attr']; |
|
| 2058 | + $attr[] = array('name' => 'name', 'value' => 'isindex'); |
|
| 2059 | 2059 | |
| 2060 | - $this->inBody(array( |
|
| 2061 | - 'name' => 'input', |
|
| 2062 | - 'type' => HTML5::STARTTAG, |
|
| 2063 | - 'attr' => $attr |
|
| 2064 | - )); |
|
| 2060 | + $this->inBody(array( |
|
| 2061 | + 'name' => 'input', |
|
| 2062 | + 'type' => HTML5::STARTTAG, |
|
| 2063 | + 'attr' => $attr |
|
| 2064 | + )); |
|
| 2065 | 2065 | |
| 2066 | - /* Act as if a stream of character tokens had been seen |
|
| 2066 | + /* Act as if a stream of character tokens had been seen |
|
| 2067 | 2067 | (see below for what they should say). */ |
| 2068 | - $this->insertText('This is a searchable index. '. |
|
| 2069 | - 'Insert your search keywords here: '); |
|
| 2068 | + $this->insertText('This is a searchable index. '. |
|
| 2069 | + 'Insert your search keywords here: '); |
|
| 2070 | 2070 | |
| 2071 | - /* Act as if an end tag token with the tag name "label" |
|
| 2071 | + /* Act as if an end tag token with the tag name "label" |
|
| 2072 | 2072 | had been seen. */ |
| 2073 | - $this->inBody(array( |
|
| 2074 | - 'name' => 'label', |
|
| 2075 | - 'type' => HTML5::ENDTAG |
|
| 2076 | - )); |
|
| 2073 | + $this->inBody(array( |
|
| 2074 | + 'name' => 'label', |
|
| 2075 | + 'type' => HTML5::ENDTAG |
|
| 2076 | + )); |
|
| 2077 | 2077 | |
| 2078 | - /* Act as if an end tag token with the tag name "p" had |
|
| 2078 | + /* Act as if an end tag token with the tag name "p" had |
|
| 2079 | 2079 | been seen. */ |
| 2080 | - $this->inBody(array( |
|
| 2081 | - 'name' => 'p', |
|
| 2082 | - 'type' => HTML5::ENDTAG |
|
| 2083 | - )); |
|
| 2080 | + $this->inBody(array( |
|
| 2081 | + 'name' => 'p', |
|
| 2082 | + 'type' => HTML5::ENDTAG |
|
| 2083 | + )); |
|
| 2084 | 2084 | |
| 2085 | - /* Act as if a start tag token with the tag name "hr" had |
|
| 2085 | + /* Act as if a start tag token with the tag name "hr" had |
|
| 2086 | 2086 | been seen. */ |
| 2087 | - $this->inBody(array( |
|
| 2088 | - 'name' => 'hr', |
|
| 2089 | - 'type' => HTML5::ENDTAG |
|
| 2090 | - )); |
|
| 2087 | + $this->inBody(array( |
|
| 2088 | + 'name' => 'hr', |
|
| 2089 | + 'type' => HTML5::ENDTAG |
|
| 2090 | + )); |
|
| 2091 | 2091 | |
| 2092 | - /* Act as if an end tag token with the tag name "form" had |
|
| 2092 | + /* Act as if an end tag token with the tag name "form" had |
|
| 2093 | 2093 | been seen. */ |
| 2094 | - $this->inBody(array( |
|
| 2095 | - 'name' => 'form', |
|
| 2096 | - 'type' => HTML5::ENDTAG |
|
| 2097 | - )); |
|
| 2098 | - } |
|
| 2099 | - break; |
|
| 2100 | - |
|
| 2101 | - /* A start tag whose tag name is "textarea" */ |
|
| 2102 | - case 'textarea': |
|
| 2103 | - $this->insertElement($token); |
|
| 2104 | - |
|
| 2105 | - /* Switch the tokeniser's content model flag to the |
|
| 2094 | + $this->inBody(array( |
|
| 2095 | + 'name' => 'form', |
|
| 2096 | + 'type' => HTML5::ENDTAG |
|
| 2097 | + )); |
|
| 2098 | + } |
|
| 2099 | + break; |
|
| 2100 | + |
|
| 2101 | + /* A start tag whose tag name is "textarea" */ |
|
| 2102 | + case 'textarea': |
|
| 2103 | + $this->insertElement($token); |
|
| 2104 | + |
|
| 2105 | + /* Switch the tokeniser's content model flag to the |
|
| 2106 | 2106 | RCDATA state. */ |
| 2107 | - return HTML5::RCDATA; |
|
| 2108 | - break; |
|
| 2107 | + return HTML5::RCDATA; |
|
| 2108 | + break; |
|
| 2109 | 2109 | |
| 2110 | - /* A start tag whose tag name is one of: "iframe", "noembed", |
|
| 2110 | + /* A start tag whose tag name is one of: "iframe", "noembed", |
|
| 2111 | 2111 | "noframes" */ |
| 2112 | - case 'iframe': case 'noembed': case 'noframes': |
|
| 2113 | - $this->insertElement($token); |
|
| 2112 | + case 'iframe': case 'noembed': case 'noframes': |
|
| 2113 | + $this->insertElement($token); |
|
| 2114 | 2114 | |
| 2115 | - /* Switch the tokeniser's content model flag to the CDATA state. */ |
|
| 2116 | - return HTML5::CDATA; |
|
| 2117 | - break; |
|
| 2115 | + /* Switch the tokeniser's content model flag to the CDATA state. */ |
|
| 2116 | + return HTML5::CDATA; |
|
| 2117 | + break; |
|
| 2118 | 2118 | |
| 2119 | - /* A start tag whose tag name is "select" */ |
|
| 2120 | - case 'select': |
|
| 2121 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 2122 | - $this->reconstructActiveFormattingElements(); |
|
| 2119 | + /* A start tag whose tag name is "select" */ |
|
| 2120 | + case 'select': |
|
| 2121 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 2122 | + $this->reconstructActiveFormattingElements(); |
|
| 2123 | 2123 | |
| 2124 | - /* Insert an HTML element for the token. */ |
|
| 2125 | - $this->insertElement($token); |
|
| 2124 | + /* Insert an HTML element for the token. */ |
|
| 2125 | + $this->insertElement($token); |
|
| 2126 | 2126 | |
| 2127 | - /* Change the insertion mode to "in select". */ |
|
| 2128 | - $this->mode = self::IN_SELECT; |
|
| 2129 | - break; |
|
| 2127 | + /* Change the insertion mode to "in select". */ |
|
| 2128 | + $this->mode = self::IN_SELECT; |
|
| 2129 | + break; |
|
| 2130 | 2130 | |
| 2131 | - /* A start or end tag whose tag name is one of: "caption", "col", |
|
| 2131 | + /* A start or end tag whose tag name is one of: "caption", "col", |
|
| 2132 | 2132 | "colgroup", "frame", "frameset", "head", "option", "optgroup", |
| 2133 | 2133 | "tbody", "td", "tfoot", "th", "thead", "tr". */ |
| 2134 | - case 'caption': case 'col': case 'colgroup': case 'frame': |
|
| 2135 | - case 'frameset': case 'head': case 'option': case 'optgroup': |
|
| 2136 | - case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead': |
|
| 2137 | - case 'tr': |
|
| 2138 | - // Parse error. Ignore the token. |
|
| 2139 | - break; |
|
| 2140 | - |
|
| 2141 | - /* A start or end tag whose tag name is one of: "event-source", |
|
| 2134 | + case 'caption': case 'col': case 'colgroup': case 'frame': |
|
| 2135 | + case 'frameset': case 'head': case 'option': case 'optgroup': |
|
| 2136 | + case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead': |
|
| 2137 | + case 'tr': |
|
| 2138 | + // Parse error. Ignore the token. |
|
| 2139 | + break; |
|
| 2140 | + |
|
| 2141 | + /* A start or end tag whose tag name is one of: "event-source", |
|
| 2142 | 2142 | "section", "nav", "article", "aside", "header", "footer", |
| 2143 | 2143 | "datagrid", "command" */ |
| 2144 | - case 'event-source': case 'section': case 'nav': case 'article': |
|
| 2145 | - case 'aside': case 'header': case 'footer': case 'datagrid': |
|
| 2146 | - case 'command': |
|
| 2147 | - // Work in progress! |
|
| 2148 | - break; |
|
| 2149 | - |
|
| 2150 | - /* A start tag token not covered by the previous entries */ |
|
| 2151 | - default: |
|
| 2152 | - /* Reconstruct the active formatting elements, if any. */ |
|
| 2153 | - $this->reconstructActiveFormattingElements(); |
|
| 2154 | - |
|
| 2155 | - $this->insertElement($token, true, true); |
|
| 2156 | - break; |
|
| 2157 | - } |
|
| 2158 | - break; |
|
| 2159 | - |
|
| 2160 | - case HTML5::ENDTAG: |
|
| 2161 | - switch($token['name']) { |
|
| 2162 | - /* An end tag with the tag name "body" */ |
|
| 2163 | - case 'body': |
|
| 2164 | - /* If the second element in the stack of open elements is |
|
| 2144 | + case 'event-source': case 'section': case 'nav': case 'article': |
|
| 2145 | + case 'aside': case 'header': case 'footer': case 'datagrid': |
|
| 2146 | + case 'command': |
|
| 2147 | + // Work in progress! |
|
| 2148 | + break; |
|
| 2149 | + |
|
| 2150 | + /* A start tag token not covered by the previous entries */ |
|
| 2151 | + default: |
|
| 2152 | + /* Reconstruct the active formatting elements, if any. */ |
|
| 2153 | + $this->reconstructActiveFormattingElements(); |
|
| 2154 | + |
|
| 2155 | + $this->insertElement($token, true, true); |
|
| 2156 | + break; |
|
| 2157 | + } |
|
| 2158 | + break; |
|
| 2159 | + |
|
| 2160 | + case HTML5::ENDTAG: |
|
| 2161 | + switch($token['name']) { |
|
| 2162 | + /* An end tag with the tag name "body" */ |
|
| 2163 | + case 'body': |
|
| 2164 | + /* If the second element in the stack of open elements is |
|
| 2165 | 2165 | not a body element, this is a parse error. Ignore the token. |
| 2166 | 2166 | (innerHTML case) */ |
| 2167 | - if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') { |
|
| 2168 | - // Ignore. |
|
| 2167 | + if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') { |
|
| 2168 | + // Ignore. |
|
| 2169 | 2169 | |
| 2170 | - /* If the current node is not the body element, then this |
|
| 2170 | + /* If the current node is not the body element, then this |
|
| 2171 | 2171 | is a parse error. */ |
| 2172 | - } elseif(end($this->stack)->nodeName !== 'body') { |
|
| 2173 | - // Parse error. |
|
| 2174 | - } |
|
| 2172 | + } elseif(end($this->stack)->nodeName !== 'body') { |
|
| 2173 | + // Parse error. |
|
| 2174 | + } |
|
| 2175 | 2175 | |
| 2176 | - /* Change the insertion mode to "after body". */ |
|
| 2177 | - $this->mode = self::AFTER_BODY; |
|
| 2178 | - break; |
|
| 2176 | + /* Change the insertion mode to "after body". */ |
|
| 2177 | + $this->mode = self::AFTER_BODY; |
|
| 2178 | + break; |
|
| 2179 | 2179 | |
| 2180 | - /* An end tag with the tag name "html" */ |
|
| 2181 | - case 'html': |
|
| 2182 | - /* Act as if an end tag with tag name "body" had been seen, |
|
| 2180 | + /* An end tag with the tag name "html" */ |
|
| 2181 | + case 'html': |
|
| 2182 | + /* Act as if an end tag with tag name "body" had been seen, |
|
| 2183 | 2183 | then, if that token wasn't ignored, reprocess the current |
| 2184 | 2184 | token. */ |
| 2185 | - $this->inBody(array( |
|
| 2186 | - 'name' => 'body', |
|
| 2187 | - 'type' => HTML5::ENDTAG |
|
| 2188 | - )); |
|
| 2185 | + $this->inBody(array( |
|
| 2186 | + 'name' => 'body', |
|
| 2187 | + 'type' => HTML5::ENDTAG |
|
| 2188 | + )); |
|
| 2189 | 2189 | |
| 2190 | - return $this->afterBody($token); |
|
| 2191 | - break; |
|
| 2190 | + return $this->afterBody($token); |
|
| 2191 | + break; |
|
| 2192 | 2192 | |
| 2193 | - /* An end tag whose tag name is one of: "address", "blockquote", |
|
| 2193 | + /* An end tag whose tag name is one of: "address", "blockquote", |
|
| 2194 | 2194 | "center", "dir", "div", "dl", "fieldset", "listing", "menu", |
| 2195 | 2195 | "ol", "pre", "ul" */ |
| 2196 | - case 'address': case 'blockquote': case 'center': case 'dir': |
|
| 2197 | - case 'div': case 'dl': case 'fieldset': case 'listing': |
|
| 2198 | - case 'menu': case 'ol': case 'pre': case 'ul': |
|
| 2199 | - /* If the stack of open elements has an element in scope |
|
| 2196 | + case 'address': case 'blockquote': case 'center': case 'dir': |
|
| 2197 | + case 'div': case 'dl': case 'fieldset': case 'listing': |
|
| 2198 | + case 'menu': case 'ol': case 'pre': case 'ul': |
|
| 2199 | + /* If the stack of open elements has an element in scope |
|
| 2200 | 2200 | with the same tag name as that of the token, then generate |
| 2201 | 2201 | implied end tags. */ |
| 2202 | - if($this->elementInScope($token['name'])) { |
|
| 2203 | - $this->generateImpliedEndTags(); |
|
| 2202 | + if($this->elementInScope($token['name'])) { |
|
| 2203 | + $this->generateImpliedEndTags(); |
|
| 2204 | 2204 | |
| 2205 | - /* Now, if the current node is not an element with |
|
| 2205 | + /* Now, if the current node is not an element with |
|
| 2206 | 2206 | the same tag name as that of the token, then this |
| 2207 | 2207 | is a parse error. */ |
| 2208 | - // w/e |
|
| 2208 | + // w/e |
|
| 2209 | 2209 | |
| 2210 | - /* If the stack of open elements has an element in |
|
| 2210 | + /* If the stack of open elements has an element in |
|
| 2211 | 2211 | scope with the same tag name as that of the token, |
| 2212 | 2212 | then pop elements from this stack until an element |
| 2213 | 2213 | with that tag name has been popped from the stack. */ |
| 2214 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2215 | - if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2216 | - $n = -1; |
|
| 2217 | - } |
|
| 2218 | - |
|
| 2219 | - array_pop($this->stack); |
|
| 2220 | - } |
|
| 2221 | - } |
|
| 2222 | - break; |
|
| 2223 | - |
|
| 2224 | - /* An end tag whose tag name is "form" */ |
|
| 2225 | - case 'form': |
|
| 2226 | - /* If the stack of open elements has an element in scope |
|
| 2214 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2215 | + if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2216 | + $n = -1; |
|
| 2217 | + } |
|
| 2218 | + |
|
| 2219 | + array_pop($this->stack); |
|
| 2220 | + } |
|
| 2221 | + } |
|
| 2222 | + break; |
|
| 2223 | + |
|
| 2224 | + /* An end tag whose tag name is "form" */ |
|
| 2225 | + case 'form': |
|
| 2226 | + /* If the stack of open elements has an element in scope |
|
| 2227 | 2227 | with the same tag name as that of the token, then generate |
| 2228 | 2228 | implied end tags. */ |
| 2229 | - if($this->elementInScope($token['name'])) { |
|
| 2230 | - $this->generateImpliedEndTags(); |
|
| 2229 | + if($this->elementInScope($token['name'])) { |
|
| 2230 | + $this->generateImpliedEndTags(); |
|
| 2231 | 2231 | |
| 2232 | - } |
|
| 2232 | + } |
|
| 2233 | 2233 | |
| 2234 | - if(end($this->stack)->nodeName !== $token['name']) { |
|
| 2235 | - /* Now, if the current node is not an element with the |
|
| 2234 | + if(end($this->stack)->nodeName !== $token['name']) { |
|
| 2235 | + /* Now, if the current node is not an element with the |
|
| 2236 | 2236 | same tag name as that of the token, then this is a parse |
| 2237 | 2237 | error. */ |
| 2238 | - // w/e |
|
| 2238 | + // w/e |
|
| 2239 | 2239 | |
| 2240 | - } else { |
|
| 2241 | - /* Otherwise, if the current node is an element with |
|
| 2240 | + } else { |
|
| 2241 | + /* Otherwise, if the current node is an element with |
|
| 2242 | 2242 | the same tag name as that of the token pop that element |
| 2243 | 2243 | from the stack. */ |
| 2244 | - array_pop($this->stack); |
|
| 2245 | - } |
|
| 2244 | + array_pop($this->stack); |
|
| 2245 | + } |
|
| 2246 | 2246 | |
| 2247 | - /* In any case, set the form element pointer to null. */ |
|
| 2248 | - $this->form_pointer = null; |
|
| 2249 | - break; |
|
| 2247 | + /* In any case, set the form element pointer to null. */ |
|
| 2248 | + $this->form_pointer = null; |
|
| 2249 | + break; |
|
| 2250 | 2250 | |
| 2251 | - /* An end tag whose tag name is "p" */ |
|
| 2252 | - case 'p': |
|
| 2253 | - /* If the stack of open elements has a p element in scope, |
|
| 2251 | + /* An end tag whose tag name is "p" */ |
|
| 2252 | + case 'p': |
|
| 2253 | + /* If the stack of open elements has a p element in scope, |
|
| 2254 | 2254 | then generate implied end tags, except for p elements. */ |
| 2255 | - if($this->elementInScope('p')) { |
|
| 2256 | - $this->generateImpliedEndTags(array('p')); |
|
| 2255 | + if($this->elementInScope('p')) { |
|
| 2256 | + $this->generateImpliedEndTags(array('p')); |
|
| 2257 | 2257 | |
| 2258 | - /* If the current node is not a p element, then this is |
|
| 2258 | + /* If the current node is not a p element, then this is |
|
| 2259 | 2259 | a parse error. */ |
| 2260 | - // k |
|
| 2260 | + // k |
|
| 2261 | 2261 | |
| 2262 | - /* If the stack of open elements has a p element in |
|
| 2262 | + /* If the stack of open elements has a p element in |
|
| 2263 | 2263 | scope, then pop elements from this stack until the stack |
| 2264 | 2264 | no longer has a p element in scope. */ |
| 2265 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2266 | - if($this->elementInScope('p')) { |
|
| 2267 | - array_pop($this->stack); |
|
| 2268 | - |
|
| 2269 | - } else { |
|
| 2270 | - break; |
|
| 2271 | - } |
|
| 2272 | - } |
|
| 2273 | - } |
|
| 2274 | - break; |
|
| 2275 | - |
|
| 2276 | - /* An end tag whose tag name is "dd", "dt", or "li" */ |
|
| 2277 | - case 'dd': case 'dt': case 'li': |
|
| 2278 | - /* If the stack of open elements has an element in scope |
|
| 2265 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2266 | + if($this->elementInScope('p')) { |
|
| 2267 | + array_pop($this->stack); |
|
| 2268 | + |
|
| 2269 | + } else { |
|
| 2270 | + break; |
|
| 2271 | + } |
|
| 2272 | + } |
|
| 2273 | + } |
|
| 2274 | + break; |
|
| 2275 | + |
|
| 2276 | + /* An end tag whose tag name is "dd", "dt", or "li" */ |
|
| 2277 | + case 'dd': case 'dt': case 'li': |
|
| 2278 | + /* If the stack of open elements has an element in scope |
|
| 2279 | 2279 | whose tag name matches the tag name of the token, then |
| 2280 | 2280 | generate implied end tags, except for elements with the |
| 2281 | 2281 | same tag name as the token. */ |
| 2282 | - if($this->elementInScope($token['name'])) { |
|
| 2283 | - $this->generateImpliedEndTags(array($token['name'])); |
|
| 2282 | + if($this->elementInScope($token['name'])) { |
|
| 2283 | + $this->generateImpliedEndTags(array($token['name'])); |
|
| 2284 | 2284 | |
| 2285 | - /* If the current node is not an element with the same |
|
| 2285 | + /* If the current node is not an element with the same |
|
| 2286 | 2286 | tag name as the token, then this is a parse error. */ |
| 2287 | - // w/e |
|
| 2287 | + // w/e |
|
| 2288 | 2288 | |
| 2289 | - /* If the stack of open elements has an element in scope |
|
| 2289 | + /* If the stack of open elements has an element in scope |
|
| 2290 | 2290 | whose tag name matches the tag name of the token, then |
| 2291 | 2291 | pop elements from this stack until an element with that |
| 2292 | 2292 | tag name has been popped from the stack. */ |
| 2293 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2294 | - if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2295 | - $n = -1; |
|
| 2296 | - } |
|
| 2293 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2294 | + if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2295 | + $n = -1; |
|
| 2296 | + } |
|
| 2297 | 2297 | |
| 2298 | - array_pop($this->stack); |
|
| 2299 | - } |
|
| 2300 | - } |
|
| 2301 | - break; |
|
| 2298 | + array_pop($this->stack); |
|
| 2299 | + } |
|
| 2300 | + } |
|
| 2301 | + break; |
|
| 2302 | 2302 | |
| 2303 | - /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4", |
|
| 2303 | + /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4", |
|
| 2304 | 2304 | "h5", "h6" */ |
| 2305 | - case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6': |
|
| 2306 | - $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'); |
|
| 2305 | + case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6': |
|
| 2306 | + $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'); |
|
| 2307 | 2307 | |
| 2308 | - /* If the stack of open elements has in scope an element whose |
|
| 2308 | + /* If the stack of open elements has in scope an element whose |
|
| 2309 | 2309 | tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then |
| 2310 | 2310 | generate implied end tags. */ |
| 2311 | - if($this->elementInScope($elements)) { |
|
| 2312 | - $this->generateImpliedEndTags(); |
|
| 2311 | + if($this->elementInScope($elements)) { |
|
| 2312 | + $this->generateImpliedEndTags(); |
|
| 2313 | 2313 | |
| 2314 | - /* Now, if the current node is not an element with the same |
|
| 2314 | + /* Now, if the current node is not an element with the same |
|
| 2315 | 2315 | tag name as that of the token, then this is a parse error. */ |
| 2316 | - // w/e |
|
| 2316 | + // w/e |
|
| 2317 | 2317 | |
| 2318 | - /* If the stack of open elements has in scope an element |
|
| 2318 | + /* If the stack of open elements has in scope an element |
|
| 2319 | 2319 | whose tag name is one of "h1", "h2", "h3", "h4", "h5", or |
| 2320 | 2320 | "h6", then pop elements from the stack until an element |
| 2321 | 2321 | with one of those tag names has been popped from the stack. */ |
| 2322 | - while($this->elementInScope($elements)) { |
|
| 2323 | - array_pop($this->stack); |
|
| 2324 | - } |
|
| 2325 | - } |
|
| 2326 | - break; |
|
| 2322 | + while($this->elementInScope($elements)) { |
|
| 2323 | + array_pop($this->stack); |
|
| 2324 | + } |
|
| 2325 | + } |
|
| 2326 | + break; |
|
| 2327 | 2327 | |
| 2328 | - /* An end tag whose tag name is one of: "a", "b", "big", "em", |
|
| 2328 | + /* An end tag whose tag name is one of: "a", "b", "big", "em", |
|
| 2329 | 2329 | "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ |
| 2330 | - case 'a': case 'b': case 'big': case 'em': case 'font': |
|
| 2331 | - case 'i': case 'nobr': case 's': case 'small': case 'strike': |
|
| 2332 | - case 'strong': case 'tt': case 'u': |
|
| 2333 | - /* 1. Let the formatting element be the last element in |
|
| 2330 | + case 'a': case 'b': case 'big': case 'em': case 'font': |
|
| 2331 | + case 'i': case 'nobr': case 's': case 'small': case 'strike': |
|
| 2332 | + case 'strong': case 'tt': case 'u': |
|
| 2333 | + /* 1. Let the formatting element be the last element in |
|
| 2334 | 2334 | the list of active formatting elements that: |
| 2335 | 2335 | * is between the end of the list and the last scope |
| 2336 | 2336 | marker in the list, if any, or the start of the list |
| 2337 | 2337 | otherwise, and |
| 2338 | 2338 | * has the same tag name as the token. |
| 2339 | 2339 | */ |
| 2340 | - while(true) { |
|
| 2341 | - for($a = count($this->a_formatting) - 1; $a >= 0; $a--) { |
|
| 2342 | - if($this->a_formatting[$a] === self::MARKER) { |
|
| 2343 | - break; |
|
| 2344 | - |
|
| 2345 | - } elseif($this->a_formatting[$a]->tagName === $token['name']) { |
|
| 2346 | - $formatting_element = $this->a_formatting[$a]; |
|
| 2347 | - $in_stack = in_array($formatting_element, $this->stack, true); |
|
| 2348 | - $fe_af_pos = $a; |
|
| 2349 | - break; |
|
| 2350 | - } |
|
| 2351 | - } |
|
| 2352 | - |
|
| 2353 | - /* If there is no such node, or, if that node is |
|
| 2340 | + while(true) { |
|
| 2341 | + for($a = count($this->a_formatting) - 1; $a >= 0; $a--) { |
|
| 2342 | + if($this->a_formatting[$a] === self::MARKER) { |
|
| 2343 | + break; |
|
| 2344 | + |
|
| 2345 | + } elseif($this->a_formatting[$a]->tagName === $token['name']) { |
|
| 2346 | + $formatting_element = $this->a_formatting[$a]; |
|
| 2347 | + $in_stack = in_array($formatting_element, $this->stack, true); |
|
| 2348 | + $fe_af_pos = $a; |
|
| 2349 | + break; |
|
| 2350 | + } |
|
| 2351 | + } |
|
| 2352 | + |
|
| 2353 | + /* If there is no such node, or, if that node is |
|
| 2354 | 2354 | also in the stack of open elements but the element |
| 2355 | 2355 | is not in scope, then this is a parse error. Abort |
| 2356 | 2356 | these steps. The token is ignored. */ |
| 2357 | - if(!isset($formatting_element) || ($in_stack && |
|
| 2358 | - !$this->elementInScope($token['name']))) { |
|
| 2359 | - break; |
|
| 2357 | + if(!isset($formatting_element) || ($in_stack && |
|
| 2358 | + !$this->elementInScope($token['name']))) { |
|
| 2359 | + break; |
|
| 2360 | 2360 | |
| 2361 | - /* Otherwise, if there is such a node, but that node |
|
| 2361 | + /* Otherwise, if there is such a node, but that node |
|
| 2362 | 2362 | is not in the stack of open elements, then this is a |
| 2363 | 2363 | parse error; remove the element from the list, and |
| 2364 | 2364 | abort these steps. */ |
| 2365 | - } elseif(isset($formatting_element) && !$in_stack) { |
|
| 2366 | - unset($this->a_formatting[$fe_af_pos]); |
|
| 2367 | - $this->a_formatting = array_merge($this->a_formatting); |
|
| 2368 | - break; |
|
| 2369 | - } |
|
| 2365 | + } elseif(isset($formatting_element) && !$in_stack) { |
|
| 2366 | + unset($this->a_formatting[$fe_af_pos]); |
|
| 2367 | + $this->a_formatting = array_merge($this->a_formatting); |
|
| 2368 | + break; |
|
| 2369 | + } |
|
| 2370 | 2370 | |
| 2371 | - /* 2. Let the furthest block be the topmost node in the |
|
| 2371 | + /* 2. Let the furthest block be the topmost node in the |
|
| 2372 | 2372 | stack of open elements that is lower in the stack |
| 2373 | 2373 | than the formatting element, and is not an element in |
| 2374 | 2374 | the phrasing or formatting categories. There might |
| 2375 | 2375 | not be one. */ |
| 2376 | - $fe_s_pos = array_search($formatting_element, $this->stack, true); |
|
| 2377 | - $length = count($this->stack); |
|
| 2376 | + $fe_s_pos = array_search($formatting_element, $this->stack, true); |
|
| 2377 | + $length = count($this->stack); |
|
| 2378 | 2378 | |
| 2379 | - for($s = $fe_s_pos + 1; $s < $length; $s++) { |
|
| 2380 | - $category = $this->getElementCategory($this->stack[$s]->nodeName); |
|
| 2379 | + for($s = $fe_s_pos + 1; $s < $length; $s++) { |
|
| 2380 | + $category = $this->getElementCategory($this->stack[$s]->nodeName); |
|
| 2381 | 2381 | |
| 2382 | - if($category !== self::PHRASING && $category !== self::FORMATTING) { |
|
| 2383 | - $furthest_block = $this->stack[$s]; |
|
| 2384 | - } |
|
| 2385 | - } |
|
| 2382 | + if($category !== self::PHRASING && $category !== self::FORMATTING) { |
|
| 2383 | + $furthest_block = $this->stack[$s]; |
|
| 2384 | + } |
|
| 2385 | + } |
|
| 2386 | 2386 | |
| 2387 | - /* 3. If there is no furthest block, then the UA must |
|
| 2387 | + /* 3. If there is no furthest block, then the UA must |
|
| 2388 | 2388 | skip the subsequent steps and instead just pop all |
| 2389 | 2389 | the nodes from the bottom of the stack of open |
| 2390 | 2390 | elements, from the current node up to the formatting |
| 2391 | 2391 | element, and remove the formatting element from the |
| 2392 | 2392 | list of active formatting elements. */ |
| 2393 | - if(!isset($furthest_block)) { |
|
| 2394 | - for($n = $length - 1; $n >= $fe_s_pos; $n--) { |
|
| 2395 | - array_pop($this->stack); |
|
| 2396 | - } |
|
| 2393 | + if(!isset($furthest_block)) { |
|
| 2394 | + for($n = $length - 1; $n >= $fe_s_pos; $n--) { |
|
| 2395 | + array_pop($this->stack); |
|
| 2396 | + } |
|
| 2397 | 2397 | |
| 2398 | - unset($this->a_formatting[$fe_af_pos]); |
|
| 2399 | - $this->a_formatting = array_merge($this->a_formatting); |
|
| 2400 | - break; |
|
| 2401 | - } |
|
| 2398 | + unset($this->a_formatting[$fe_af_pos]); |
|
| 2399 | + $this->a_formatting = array_merge($this->a_formatting); |
|
| 2400 | + break; |
|
| 2401 | + } |
|
| 2402 | 2402 | |
| 2403 | - /* 4. Let the common ancestor be the element |
|
| 2403 | + /* 4. Let the common ancestor be the element |
|
| 2404 | 2404 | immediately above the formatting element in the stack |
| 2405 | 2405 | of open elements. */ |
| 2406 | - $common_ancestor = $this->stack[$fe_s_pos - 1]; |
|
| 2406 | + $common_ancestor = $this->stack[$fe_s_pos - 1]; |
|
| 2407 | 2407 | |
| 2408 | - /* 5. If the furthest block has a parent node, then |
|
| 2408 | + /* 5. If the furthest block has a parent node, then |
|
| 2409 | 2409 | remove the furthest block from its parent node. */ |
| 2410 | - if($furthest_block->parentNode !== null) { |
|
| 2411 | - $furthest_block->parentNode->removeChild($furthest_block); |
|
| 2412 | - } |
|
| 2410 | + if($furthest_block->parentNode !== null) { |
|
| 2411 | + $furthest_block->parentNode->removeChild($furthest_block); |
|
| 2412 | + } |
|
| 2413 | 2413 | |
| 2414 | - /* 6. Let a bookmark note the position of the |
|
| 2414 | + /* 6. Let a bookmark note the position of the |
|
| 2415 | 2415 | formatting element in the list of active formatting |
| 2416 | 2416 | elements relative to the elements on either side |
| 2417 | 2417 | of it in the list. */ |
| 2418 | - $bookmark = $fe_af_pos; |
|
| 2418 | + $bookmark = $fe_af_pos; |
|
| 2419 | 2419 | |
| 2420 | - /* 7. Let node and last node be the furthest block. |
|
| 2420 | + /* 7. Let node and last node be the furthest block. |
|
| 2421 | 2421 | Follow these steps: */ |
| 2422 | - $node = $furthest_block; |
|
| 2423 | - $last_node = $furthest_block; |
|
| 2422 | + $node = $furthest_block; |
|
| 2423 | + $last_node = $furthest_block; |
|
| 2424 | 2424 | |
| 2425 | - while(true) { |
|
| 2426 | - for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) { |
|
| 2427 | - /* 7.1 Let node be the element immediately |
|
| 2425 | + while(true) { |
|
| 2426 | + for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) { |
|
| 2427 | + /* 7.1 Let node be the element immediately |
|
| 2428 | 2428 | prior to node in the stack of open elements. */ |
| 2429 | - $node = $this->stack[$n]; |
|
| 2429 | + $node = $this->stack[$n]; |
|
| 2430 | 2430 | |
| 2431 | - /* 7.2 If node is not in the list of active |
|
| 2431 | + /* 7.2 If node is not in the list of active |
|
| 2432 | 2432 | formatting elements, then remove node from |
| 2433 | 2433 | the stack of open elements and then go back |
| 2434 | 2434 | to step 1. */ |
| 2435 | - if(!in_array($node, $this->a_formatting, true)) { |
|
| 2436 | - unset($this->stack[$n]); |
|
| 2437 | - $this->stack = array_merge($this->stack); |
|
| 2435 | + if(!in_array($node, $this->a_formatting, true)) { |
|
| 2436 | + unset($this->stack[$n]); |
|
| 2437 | + $this->stack = array_merge($this->stack); |
|
| 2438 | 2438 | |
| 2439 | - } else { |
|
| 2440 | - break; |
|
| 2441 | - } |
|
| 2442 | - } |
|
| 2439 | + } else { |
|
| 2440 | + break; |
|
| 2441 | + } |
|
| 2442 | + } |
|
| 2443 | 2443 | |
| 2444 | - /* 7.3 Otherwise, if node is the formatting |
|
| 2444 | + /* 7.3 Otherwise, if node is the formatting |
|
| 2445 | 2445 | element, then go to the next step in the overall |
| 2446 | 2446 | algorithm. */ |
| 2447 | - if($node === $formatting_element) { |
|
| 2448 | - break; |
|
| 2447 | + if($node === $formatting_element) { |
|
| 2448 | + break; |
|
| 2449 | 2449 | |
| 2450 | - /* 7.4 Otherwise, if last node is the furthest |
|
| 2450 | + /* 7.4 Otherwise, if last node is the furthest |
|
| 2451 | 2451 | block, then move the aforementioned bookmark to |
| 2452 | 2452 | be immediately after the node in the list of |
| 2453 | 2453 | active formatting elements. */ |
| 2454 | - } elseif($last_node === $furthest_block) { |
|
| 2455 | - $bookmark = array_search($node, $this->a_formatting, true) + 1; |
|
| 2456 | - } |
|
| 2454 | + } elseif($last_node === $furthest_block) { |
|
| 2455 | + $bookmark = array_search($node, $this->a_formatting, true) + 1; |
|
| 2456 | + } |
|
| 2457 | 2457 | |
| 2458 | - /* 7.5 If node has any children, perform a |
|
| 2458 | + /* 7.5 If node has any children, perform a |
|
| 2459 | 2459 | shallow clone of node, replace the entry for |
| 2460 | 2460 | node in the list of active formatting elements |
| 2461 | 2461 | with an entry for the clone, replace the entry |
| 2462 | 2462 | for node in the stack of open elements with an |
| 2463 | 2463 | entry for the clone, and let node be the clone. */ |
| 2464 | - if($node->hasChildNodes()) { |
|
| 2465 | - $clone = $node->cloneNode(); |
|
| 2466 | - $s_pos = array_search($node, $this->stack, true); |
|
| 2467 | - $a_pos = array_search($node, $this->a_formatting, true); |
|
| 2464 | + if($node->hasChildNodes()) { |
|
| 2465 | + $clone = $node->cloneNode(); |
|
| 2466 | + $s_pos = array_search($node, $this->stack, true); |
|
| 2467 | + $a_pos = array_search($node, $this->a_formatting, true); |
|
| 2468 | 2468 | |
| 2469 | - $this->stack[$s_pos] = $clone; |
|
| 2470 | - $this->a_formatting[$a_pos] = $clone; |
|
| 2471 | - $node = $clone; |
|
| 2472 | - } |
|
| 2469 | + $this->stack[$s_pos] = $clone; |
|
| 2470 | + $this->a_formatting[$a_pos] = $clone; |
|
| 2471 | + $node = $clone; |
|
| 2472 | + } |
|
| 2473 | 2473 | |
| 2474 | - /* 7.6 Insert last node into node, first removing |
|
| 2474 | + /* 7.6 Insert last node into node, first removing |
|
| 2475 | 2475 | it from its previous parent node if any. */ |
| 2476 | - if($last_node->parentNode !== null) { |
|
| 2477 | - $last_node->parentNode->removeChild($last_node); |
|
| 2478 | - } |
|
| 2476 | + if($last_node->parentNode !== null) { |
|
| 2477 | + $last_node->parentNode->removeChild($last_node); |
|
| 2478 | + } |
|
| 2479 | 2479 | |
| 2480 | - $node->appendChild($last_node); |
|
| 2480 | + $node->appendChild($last_node); |
|
| 2481 | 2481 | |
| 2482 | - /* 7.7 Let last node be node. */ |
|
| 2483 | - $last_node = $node; |
|
| 2484 | - } |
|
| 2482 | + /* 7.7 Let last node be node. */ |
|
| 2483 | + $last_node = $node; |
|
| 2484 | + } |
|
| 2485 | 2485 | |
| 2486 | - /* 8. Insert whatever last node ended up being in |
|
| 2486 | + /* 8. Insert whatever last node ended up being in |
|
| 2487 | 2487 | the previous step into the common ancestor node, |
| 2488 | 2488 | first removing it from its previous parent node if |
| 2489 | 2489 | any. */ |
| 2490 | - if($last_node->parentNode !== null) { |
|
| 2491 | - $last_node->parentNode->removeChild($last_node); |
|
| 2492 | - } |
|
| 2490 | + if($last_node->parentNode !== null) { |
|
| 2491 | + $last_node->parentNode->removeChild($last_node); |
|
| 2492 | + } |
|
| 2493 | 2493 | |
| 2494 | - $common_ancestor->appendChild($last_node); |
|
| 2494 | + $common_ancestor->appendChild($last_node); |
|
| 2495 | 2495 | |
| 2496 | - /* 9. Perform a shallow clone of the formatting |
|
| 2496 | + /* 9. Perform a shallow clone of the formatting |
|
| 2497 | 2497 | element. */ |
| 2498 | - $clone = $formatting_element->cloneNode(); |
|
| 2498 | + $clone = $formatting_element->cloneNode(); |
|
| 2499 | 2499 | |
| 2500 | - /* 10. Take all of the child nodes of the furthest |
|
| 2500 | + /* 10. Take all of the child nodes of the furthest |
|
| 2501 | 2501 | block and append them to the clone created in the |
| 2502 | 2502 | last step. */ |
| 2503 | - while($furthest_block->hasChildNodes()) { |
|
| 2504 | - $child = $furthest_block->firstChild; |
|
| 2505 | - $furthest_block->removeChild($child); |
|
| 2506 | - $clone->appendChild($child); |
|
| 2507 | - } |
|
| 2503 | + while($furthest_block->hasChildNodes()) { |
|
| 2504 | + $child = $furthest_block->firstChild; |
|
| 2505 | + $furthest_block->removeChild($child); |
|
| 2506 | + $clone->appendChild($child); |
|
| 2507 | + } |
|
| 2508 | 2508 | |
| 2509 | - /* 11. Append that clone to the furthest block. */ |
|
| 2510 | - $furthest_block->appendChild($clone); |
|
| 2509 | + /* 11. Append that clone to the furthest block. */ |
|
| 2510 | + $furthest_block->appendChild($clone); |
|
| 2511 | 2511 | |
| 2512 | - /* 12. Remove the formatting element from the list |
|
| 2512 | + /* 12. Remove the formatting element from the list |
|
| 2513 | 2513 | of active formatting elements, and insert the clone |
| 2514 | 2514 | into the list of active formatting elements at the |
| 2515 | 2515 | position of the aforementioned bookmark. */ |
| 2516 | - $fe_af_pos = array_search($formatting_element, $this->a_formatting, true); |
|
| 2517 | - unset($this->a_formatting[$fe_af_pos]); |
|
| 2518 | - $this->a_formatting = array_merge($this->a_formatting); |
|
| 2516 | + $fe_af_pos = array_search($formatting_element, $this->a_formatting, true); |
|
| 2517 | + unset($this->a_formatting[$fe_af_pos]); |
|
| 2518 | + $this->a_formatting = array_merge($this->a_formatting); |
|
| 2519 | 2519 | |
| 2520 | - $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1); |
|
| 2521 | - $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting)); |
|
| 2522 | - $this->a_formatting = array_merge($af_part1, array($clone), $af_part2); |
|
| 2520 | + $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1); |
|
| 2521 | + $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting)); |
|
| 2522 | + $this->a_formatting = array_merge($af_part1, array($clone), $af_part2); |
|
| 2523 | 2523 | |
| 2524 | - /* 13. Remove the formatting element from the stack |
|
| 2524 | + /* 13. Remove the formatting element from the stack |
|
| 2525 | 2525 | of open elements, and insert the clone into the stack |
| 2526 | 2526 | of open elements immediately after (i.e. in a more |
| 2527 | 2527 | deeply nested position than) the position of the |
| 2528 | 2528 | furthest block in that stack. */ |
| 2529 | - $fe_s_pos = array_search($formatting_element, $this->stack, true); |
|
| 2530 | - $fb_s_pos = array_search($furthest_block, $this->stack, true); |
|
| 2531 | - unset($this->stack[$fe_s_pos]); |
|
| 2529 | + $fe_s_pos = array_search($formatting_element, $this->stack, true); |
|
| 2530 | + $fb_s_pos = array_search($furthest_block, $this->stack, true); |
|
| 2531 | + unset($this->stack[$fe_s_pos]); |
|
| 2532 | 2532 | |
| 2533 | - $s_part1 = array_slice($this->stack, 0, $fb_s_pos); |
|
| 2534 | - $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack)); |
|
| 2535 | - $this->stack = array_merge($s_part1, array($clone), $s_part2); |
|
| 2533 | + $s_part1 = array_slice($this->stack, 0, $fb_s_pos); |
|
| 2534 | + $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack)); |
|
| 2535 | + $this->stack = array_merge($s_part1, array($clone), $s_part2); |
|
| 2536 | 2536 | |
| 2537 | - /* 14. Jump back to step 1 in this series of steps. */ |
|
| 2538 | - unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block); |
|
| 2539 | - } |
|
| 2540 | - break; |
|
| 2537 | + /* 14. Jump back to step 1 in this series of steps. */ |
|
| 2538 | + unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block); |
|
| 2539 | + } |
|
| 2540 | + break; |
|
| 2541 | 2541 | |
| 2542 | - /* An end tag token whose tag name is one of: "button", |
|
| 2542 | + /* An end tag token whose tag name is one of: "button", |
|
| 2543 | 2543 | "marquee", "object" */ |
| 2544 | - case 'button': case 'marquee': case 'object': |
|
| 2545 | - /* If the stack of open elements has an element in scope whose |
|
| 2544 | + case 'button': case 'marquee': case 'object': |
|
| 2545 | + /* If the stack of open elements has an element in scope whose |
|
| 2546 | 2546 | tag name matches the tag name of the token, then generate implied |
| 2547 | 2547 | tags. */ |
| 2548 | - if($this->elementInScope($token['name'])) { |
|
| 2549 | - $this->generateImpliedEndTags(); |
|
| 2548 | + if($this->elementInScope($token['name'])) { |
|
| 2549 | + $this->generateImpliedEndTags(); |
|
| 2550 | 2550 | |
| 2551 | - /* Now, if the current node is not an element with the same |
|
| 2551 | + /* Now, if the current node is not an element with the same |
|
| 2552 | 2552 | tag name as the token, then this is a parse error. */ |
| 2553 | - // k |
|
| 2553 | + // k |
|
| 2554 | 2554 | |
| 2555 | - /* Now, if the stack of open elements has an element in scope |
|
| 2555 | + /* Now, if the stack of open elements has an element in scope |
|
| 2556 | 2556 | whose tag name matches the tag name of the token, then pop |
| 2557 | 2557 | elements from the stack until that element has been popped from |
| 2558 | 2558 | the stack, and clear the list of active formatting elements up |
| 2559 | 2559 | to the last marker. */ |
| 2560 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2561 | - if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2562 | - $n = -1; |
|
| 2563 | - } |
|
| 2560 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2561 | + if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2562 | + $n = -1; |
|
| 2563 | + } |
|
| 2564 | 2564 | |
| 2565 | - array_pop($this->stack); |
|
| 2566 | - } |
|
| 2565 | + array_pop($this->stack); |
|
| 2566 | + } |
|
| 2567 | 2567 | |
| 2568 | - $marker = end(array_keys($this->a_formatting, self::MARKER, true)); |
|
| 2568 | + $marker = end(array_keys($this->a_formatting, self::MARKER, true)); |
|
| 2569 | 2569 | |
| 2570 | - for($n = count($this->a_formatting) - 1; $n > $marker; $n--) { |
|
| 2571 | - array_pop($this->a_formatting); |
|
| 2572 | - } |
|
| 2573 | - } |
|
| 2574 | - break; |
|
| 2570 | + for($n = count($this->a_formatting) - 1; $n > $marker; $n--) { |
|
| 2571 | + array_pop($this->a_formatting); |
|
| 2572 | + } |
|
| 2573 | + } |
|
| 2574 | + break; |
|
| 2575 | 2575 | |
| 2576 | - /* Or an end tag whose tag name is one of: "area", "basefont", |
|
| 2576 | + /* Or an end tag whose tag name is one of: "area", "basefont", |
|
| 2577 | 2577 | "bgsound", "br", "embed", "hr", "iframe", "image", "img", |
| 2578 | 2578 | "input", "isindex", "noembed", "noframes", "param", "select", |
| 2579 | 2579 | "spacer", "table", "textarea", "wbr" */ |
| 2580 | - case 'area': case 'basefont': case 'bgsound': case 'br': |
|
| 2581 | - case 'embed': case 'hr': case 'iframe': case 'image': |
|
| 2582 | - case 'img': case 'input': case 'isindex': case 'noembed': |
|
| 2583 | - case 'noframes': case 'param': case 'select': case 'spacer': |
|
| 2584 | - case 'table': case 'textarea': case 'wbr': |
|
| 2585 | - // Parse error. Ignore the token. |
|
| 2586 | - break; |
|
| 2587 | - |
|
| 2588 | - /* An end tag token not covered by the previous entries */ |
|
| 2589 | - default: |
|
| 2590 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2591 | - /* Initialise node to be the current node (the bottommost |
|
| 2580 | + case 'area': case 'basefont': case 'bgsound': case 'br': |
|
| 2581 | + case 'embed': case 'hr': case 'iframe': case 'image': |
|
| 2582 | + case 'img': case 'input': case 'isindex': case 'noembed': |
|
| 2583 | + case 'noframes': case 'param': case 'select': case 'spacer': |
|
| 2584 | + case 'table': case 'textarea': case 'wbr': |
|
| 2585 | + // Parse error. Ignore the token. |
|
| 2586 | + break; |
|
| 2587 | + |
|
| 2588 | + /* An end tag token not covered by the previous entries */ |
|
| 2589 | + default: |
|
| 2590 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2591 | + /* Initialise node to be the current node (the bottommost |
|
| 2592 | 2592 | node of the stack). */ |
| 2593 | - $node = end($this->stack); |
|
| 2593 | + $node = end($this->stack); |
|
| 2594 | 2594 | |
| 2595 | - /* If node has the same tag name as the end tag token, |
|
| 2595 | + /* If node has the same tag name as the end tag token, |
|
| 2596 | 2596 | then: */ |
| 2597 | - if($token['name'] === $node->nodeName) { |
|
| 2598 | - /* Generate implied end tags. */ |
|
| 2599 | - $this->generateImpliedEndTags(); |
|
| 2597 | + if($token['name'] === $node->nodeName) { |
|
| 2598 | + /* Generate implied end tags. */ |
|
| 2599 | + $this->generateImpliedEndTags(); |
|
| 2600 | 2600 | |
| 2601 | - /* If the tag name of the end tag token does not |
|
| 2601 | + /* If the tag name of the end tag token does not |
|
| 2602 | 2602 | match the tag name of the current node, this is a |
| 2603 | 2603 | parse error. */ |
| 2604 | - // k |
|
| 2604 | + // k |
|
| 2605 | 2605 | |
| 2606 | - /* Pop all the nodes from the current node up to |
|
| 2606 | + /* Pop all the nodes from the current node up to |
|
| 2607 | 2607 | node, including node, then stop this algorithm. */ |
| 2608 | - for($x = count($this->stack) - $n; $x >= $n; $x--) { |
|
| 2609 | - array_pop($this->stack); |
|
| 2610 | - } |
|
| 2608 | + for($x = count($this->stack) - $n; $x >= $n; $x--) { |
|
| 2609 | + array_pop($this->stack); |
|
| 2610 | + } |
|
| 2611 | 2611 | |
| 2612 | - } else { |
|
| 2613 | - $category = $this->getElementCategory($node); |
|
| 2612 | + } else { |
|
| 2613 | + $category = $this->getElementCategory($node); |
|
| 2614 | 2614 | |
| 2615 | - if($category !== self::SPECIAL && $category !== self::SCOPING) { |
|
| 2616 | - /* Otherwise, if node is in neither the formatting |
|
| 2615 | + if($category !== self::SPECIAL && $category !== self::SCOPING) { |
|
| 2616 | + /* Otherwise, if node is in neither the formatting |
|
| 2617 | 2617 | category nor the phrasing category, then this is a |
| 2618 | 2618 | parse error. Stop this algorithm. The end tag token |
| 2619 | 2619 | is ignored. */ |
| 2620 | - return false; |
|
| 2621 | - } |
|
| 2622 | - } |
|
| 2623 | - } |
|
| 2624 | - break; |
|
| 2625 | - } |
|
| 2626 | - break; |
|
| 2627 | - } |
|
| 2628 | - } |
|
| 2629 | - |
|
| 2630 | - private function inTable($token) { |
|
| 2631 | - $clear = array('html', 'table'); |
|
| 2632 | - |
|
| 2633 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 2620 | + return false; |
|
| 2621 | + } |
|
| 2622 | + } |
|
| 2623 | + } |
|
| 2624 | + break; |
|
| 2625 | + } |
|
| 2626 | + break; |
|
| 2627 | + } |
|
| 2628 | + } |
|
| 2629 | + |
|
| 2630 | + private function inTable($token) { |
|
| 2631 | + $clear = array('html', 'table'); |
|
| 2632 | + |
|
| 2633 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 2634 | 2634 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 2635 | 2635 | or U+0020 SPACE */ |
| 2636 | - if($token['type'] === HTML5::CHARACTR && |
|
| 2637 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 2638 | - /* Append the character to the current node. */ |
|
| 2639 | - $text = $this->dom->createTextNode($token['data']); |
|
| 2640 | - end($this->stack)->appendChild($text); |
|
| 2641 | - |
|
| 2642 | - /* A comment token */ |
|
| 2643 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 2644 | - /* Append a Comment node to the current node with the data |
|
| 2636 | + if($token['type'] === HTML5::CHARACTR && |
|
| 2637 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 2638 | + /* Append the character to the current node. */ |
|
| 2639 | + $text = $this->dom->createTextNode($token['data']); |
|
| 2640 | + end($this->stack)->appendChild($text); |
|
| 2641 | + |
|
| 2642 | + /* A comment token */ |
|
| 2643 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 2644 | + /* Append a Comment node to the current node with the data |
|
| 2645 | 2645 | attribute set to the data given in the comment token. */ |
| 2646 | - $comment = $this->dom->createComment($token['data']); |
|
| 2647 | - end($this->stack)->appendChild($comment); |
|
| 2646 | + $comment = $this->dom->createComment($token['data']); |
|
| 2647 | + end($this->stack)->appendChild($comment); |
|
| 2648 | 2648 | |
| 2649 | - /* A start tag whose tag name is "caption" */ |
|
| 2650 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2651 | - $token['name'] === 'caption') { |
|
| 2652 | - /* Clear the stack back to a table context. */ |
|
| 2653 | - $this->clearStackToTableContext($clear); |
|
| 2649 | + /* A start tag whose tag name is "caption" */ |
|
| 2650 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2651 | + $token['name'] === 'caption') { |
|
| 2652 | + /* Clear the stack back to a table context. */ |
|
| 2653 | + $this->clearStackToTableContext($clear); |
|
| 2654 | 2654 | |
| 2655 | - /* Insert a marker at the end of the list of active |
|
| 2655 | + /* Insert a marker at the end of the list of active |
|
| 2656 | 2656 | formatting elements. */ |
| 2657 | - $this->a_formatting[] = self::MARKER; |
|
| 2657 | + $this->a_formatting[] = self::MARKER; |
|
| 2658 | 2658 | |
| 2659 | - /* Insert an HTML element for the token, then switch the |
|
| 2659 | + /* Insert an HTML element for the token, then switch the |
|
| 2660 | 2660 | insertion mode to "in caption". */ |
| 2661 | - $this->insertElement($token); |
|
| 2662 | - $this->mode = self::IN_CAPTION; |
|
| 2661 | + $this->insertElement($token); |
|
| 2662 | + $this->mode = self::IN_CAPTION; |
|
| 2663 | 2663 | |
| 2664 | - /* A start tag whose tag name is "colgroup" */ |
|
| 2665 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2666 | - $token['name'] === 'colgroup') { |
|
| 2667 | - /* Clear the stack back to a table context. */ |
|
| 2668 | - $this->clearStackToTableContext($clear); |
|
| 2664 | + /* A start tag whose tag name is "colgroup" */ |
|
| 2665 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2666 | + $token['name'] === 'colgroup') { |
|
| 2667 | + /* Clear the stack back to a table context. */ |
|
| 2668 | + $this->clearStackToTableContext($clear); |
|
| 2669 | 2669 | |
| 2670 | - /* Insert an HTML element for the token, then switch the |
|
| 2670 | + /* Insert an HTML element for the token, then switch the |
|
| 2671 | 2671 | insertion mode to "in column group". */ |
| 2672 | - $this->insertElement($token); |
|
| 2673 | - $this->mode = self::IN_CGROUP; |
|
| 2674 | - |
|
| 2675 | - /* A start tag whose tag name is "col" */ |
|
| 2676 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2677 | - $token['name'] === 'col') { |
|
| 2678 | - $this->inTable(array( |
|
| 2679 | - 'name' => 'colgroup', |
|
| 2680 | - 'type' => HTML5::STARTTAG, |
|
| 2681 | - 'attr' => array() |
|
| 2682 | - )); |
|
| 2683 | - |
|
| 2684 | - $this->inColumnGroup($token); |
|
| 2685 | - |
|
| 2686 | - /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
|
| 2687 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2688 | - array('tbody', 'tfoot', 'thead'))) { |
|
| 2689 | - /* Clear the stack back to a table context. */ |
|
| 2690 | - $this->clearStackToTableContext($clear); |
|
| 2691 | - |
|
| 2692 | - /* Insert an HTML element for the token, then switch the insertion |
|
| 2672 | + $this->insertElement($token); |
|
| 2673 | + $this->mode = self::IN_CGROUP; |
|
| 2674 | + |
|
| 2675 | + /* A start tag whose tag name is "col" */ |
|
| 2676 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2677 | + $token['name'] === 'col') { |
|
| 2678 | + $this->inTable(array( |
|
| 2679 | + 'name' => 'colgroup', |
|
| 2680 | + 'type' => HTML5::STARTTAG, |
|
| 2681 | + 'attr' => array() |
|
| 2682 | + )); |
|
| 2683 | + |
|
| 2684 | + $this->inColumnGroup($token); |
|
| 2685 | + |
|
| 2686 | + /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
|
| 2687 | + } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2688 | + array('tbody', 'tfoot', 'thead'))) { |
|
| 2689 | + /* Clear the stack back to a table context. */ |
|
| 2690 | + $this->clearStackToTableContext($clear); |
|
| 2691 | + |
|
| 2692 | + /* Insert an HTML element for the token, then switch the insertion |
|
| 2693 | 2693 | mode to "in table body". */ |
| 2694 | - $this->insertElement($token); |
|
| 2695 | - $this->mode = self::IN_TBODY; |
|
| 2694 | + $this->insertElement($token); |
|
| 2695 | + $this->mode = self::IN_TBODY; |
|
| 2696 | 2696 | |
| 2697 | - /* A start tag whose tag name is one of: "td", "th", "tr" */ |
|
| 2698 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2699 | - in_array($token['name'], array('td', 'th', 'tr'))) { |
|
| 2700 | - /* Act as if a start tag token with the tag name "tbody" had been |
|
| 2697 | + /* A start tag whose tag name is one of: "td", "th", "tr" */ |
|
| 2698 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2699 | + in_array($token['name'], array('td', 'th', 'tr'))) { |
|
| 2700 | + /* Act as if a start tag token with the tag name "tbody" had been |
|
| 2701 | 2701 | seen, then reprocess the current token. */ |
| 2702 | - $this->inTable(array( |
|
| 2703 | - 'name' => 'tbody', |
|
| 2704 | - 'type' => HTML5::STARTTAG, |
|
| 2705 | - 'attr' => array() |
|
| 2706 | - )); |
|
| 2707 | - |
|
| 2708 | - return $this->inTableBody($token); |
|
| 2709 | - |
|
| 2710 | - /* A start tag whose tag name is "table" */ |
|
| 2711 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2712 | - $token['name'] === 'table') { |
|
| 2713 | - /* Parse error. Act as if an end tag token with the tag name "table" |
|
| 2702 | + $this->inTable(array( |
|
| 2703 | + 'name' => 'tbody', |
|
| 2704 | + 'type' => HTML5::STARTTAG, |
|
| 2705 | + 'attr' => array() |
|
| 2706 | + )); |
|
| 2707 | + |
|
| 2708 | + return $this->inTableBody($token); |
|
| 2709 | + |
|
| 2710 | + /* A start tag whose tag name is "table" */ |
|
| 2711 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2712 | + $token['name'] === 'table') { |
|
| 2713 | + /* Parse error. Act as if an end tag token with the tag name "table" |
|
| 2714 | 2714 | had been seen, then, if that token wasn't ignored, reprocess the |
| 2715 | 2715 | current token. */ |
| 2716 | - $this->inTable(array( |
|
| 2717 | - 'name' => 'table', |
|
| 2718 | - 'type' => HTML5::ENDTAG |
|
| 2719 | - )); |
|
| 2716 | + $this->inTable(array( |
|
| 2717 | + 'name' => 'table', |
|
| 2718 | + 'type' => HTML5::ENDTAG |
|
| 2719 | + )); |
|
| 2720 | 2720 | |
| 2721 | - return $this->mainPhase($token); |
|
| 2721 | + return $this->mainPhase($token); |
|
| 2722 | 2722 | |
| 2723 | - /* An end tag whose tag name is "table" */ |
|
| 2724 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2725 | - $token['name'] === 'table') { |
|
| 2726 | - /* If the stack of open elements does not have an element in table |
|
| 2723 | + /* An end tag whose tag name is "table" */ |
|
| 2724 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2725 | + $token['name'] === 'table') { |
|
| 2726 | + /* If the stack of open elements does not have an element in table |
|
| 2727 | 2727 | scope with the same tag name as the token, this is a parse error. |
| 2728 | 2728 | Ignore the token. (innerHTML case) */ |
| 2729 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 2730 | - return false; |
|
| 2729 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 2730 | + return false; |
|
| 2731 | 2731 | |
| 2732 | - /* Otherwise: */ |
|
| 2733 | - } else { |
|
| 2734 | - /* Generate implied end tags. */ |
|
| 2735 | - $this->generateImpliedEndTags(); |
|
| 2732 | + /* Otherwise: */ |
|
| 2733 | + } else { |
|
| 2734 | + /* Generate implied end tags. */ |
|
| 2735 | + $this->generateImpliedEndTags(); |
|
| 2736 | 2736 | |
| 2737 | - /* Now, if the current node is not a table element, then this |
|
| 2737 | + /* Now, if the current node is not a table element, then this |
|
| 2738 | 2738 | is a parse error. */ |
| 2739 | - // w/e |
|
| 2739 | + // w/e |
|
| 2740 | 2740 | |
| 2741 | - /* Pop elements from this stack until a table element has been |
|
| 2741 | + /* Pop elements from this stack until a table element has been |
|
| 2742 | 2742 | popped from the stack. */ |
| 2743 | - while(true) { |
|
| 2744 | - $current = end($this->stack)->nodeName; |
|
| 2745 | - array_pop($this->stack); |
|
| 2743 | + while(true) { |
|
| 2744 | + $current = end($this->stack)->nodeName; |
|
| 2745 | + array_pop($this->stack); |
|
| 2746 | 2746 | |
| 2747 | - if($current === 'table') { |
|
| 2748 | - break; |
|
| 2749 | - } |
|
| 2750 | - } |
|
| 2747 | + if($current === 'table') { |
|
| 2748 | + break; |
|
| 2749 | + } |
|
| 2750 | + } |
|
| 2751 | 2751 | |
| 2752 | - /* Reset the insertion mode appropriately. */ |
|
| 2753 | - $this->resetInsertionMode(); |
|
| 2754 | - } |
|
| 2752 | + /* Reset the insertion mode appropriately. */ |
|
| 2753 | + $this->resetInsertionMode(); |
|
| 2754 | + } |
|
| 2755 | 2755 | |
| 2756 | - /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 2756 | + /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 2757 | 2757 | "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 2758 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2759 | - array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td', |
|
| 2760 | - 'tfoot', 'th', 'thead', 'tr'))) { |
|
| 2761 | - // Parse error. Ignore the token. |
|
| 2762 | - |
|
| 2763 | - /* Anything else */ |
|
| 2764 | - } else { |
|
| 2765 | - /* Parse error. Process the token as if the insertion mode was "in |
|
| 2758 | + } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2759 | + array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td', |
|
| 2760 | + 'tfoot', 'th', 'thead', 'tr'))) { |
|
| 2761 | + // Parse error. Ignore the token. |
|
| 2762 | + |
|
| 2763 | + /* Anything else */ |
|
| 2764 | + } else { |
|
| 2765 | + /* Parse error. Process the token as if the insertion mode was "in |
|
| 2766 | 2766 | body", with the following exception: */ |
| 2767 | 2767 | |
| 2768 | - /* If the current node is a table, tbody, tfoot, thead, or tr |
|
| 2768 | + /* If the current node is a table, tbody, tfoot, thead, or tr |
|
| 2769 | 2769 | element, then, whenever a node would be inserted into the current |
| 2770 | 2770 | node, it must instead be inserted into the foster parent element. */ |
| 2771 | - if(in_array(end($this->stack)->nodeName, |
|
| 2772 | - array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { |
|
| 2773 | - /* The foster parent element is the parent element of the last |
|
| 2771 | + if(in_array(end($this->stack)->nodeName, |
|
| 2772 | + array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { |
|
| 2773 | + /* The foster parent element is the parent element of the last |
|
| 2774 | 2774 | table element in the stack of open elements, if there is a |
| 2775 | 2775 | table element and it has such a parent element. If there is no |
| 2776 | 2776 | table element in the stack of open elements (innerHTML case), |
@@ -2781,1124 +2781,1124 @@ discard block |
||
| 2781 | 2781 | its parent node is not an element, then the foster parent |
| 2782 | 2782 | element is the element before the last table element in the |
| 2783 | 2783 | stack of open elements. */ |
| 2784 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2785 | - if($this->stack[$n]->nodeName === 'table') { |
|
| 2786 | - $table = $this->stack[$n]; |
|
| 2787 | - break; |
|
| 2788 | - } |
|
| 2789 | - } |
|
| 2790 | - |
|
| 2791 | - if(isset($table) && $table->parentNode !== null) { |
|
| 2792 | - $this->foster_parent = $table->parentNode; |
|
| 2793 | - |
|
| 2794 | - } elseif(!isset($table)) { |
|
| 2795 | - $this->foster_parent = $this->stack[0]; |
|
| 2796 | - |
|
| 2797 | - } elseif(isset($table) && ($table->parentNode === null || |
|
| 2798 | - $table->parentNode->nodeType !== XML_ELEMENT_NODE)) { |
|
| 2799 | - $this->foster_parent = $this->stack[$n - 1]; |
|
| 2800 | - } |
|
| 2801 | - } |
|
| 2802 | - |
|
| 2803 | - $this->inBody($token); |
|
| 2804 | - } |
|
| 2805 | - } |
|
| 2806 | - |
|
| 2807 | - private function inCaption($token) { |
|
| 2808 | - /* An end tag whose tag name is "caption" */ |
|
| 2809 | - if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { |
|
| 2810 | - /* If the stack of open elements does not have an element in table |
|
| 2784 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2785 | + if($this->stack[$n]->nodeName === 'table') { |
|
| 2786 | + $table = $this->stack[$n]; |
|
| 2787 | + break; |
|
| 2788 | + } |
|
| 2789 | + } |
|
| 2790 | + |
|
| 2791 | + if(isset($table) && $table->parentNode !== null) { |
|
| 2792 | + $this->foster_parent = $table->parentNode; |
|
| 2793 | + |
|
| 2794 | + } elseif(!isset($table)) { |
|
| 2795 | + $this->foster_parent = $this->stack[0]; |
|
| 2796 | + |
|
| 2797 | + } elseif(isset($table) && ($table->parentNode === null || |
|
| 2798 | + $table->parentNode->nodeType !== XML_ELEMENT_NODE)) { |
|
| 2799 | + $this->foster_parent = $this->stack[$n - 1]; |
|
| 2800 | + } |
|
| 2801 | + } |
|
| 2802 | + |
|
| 2803 | + $this->inBody($token); |
|
| 2804 | + } |
|
| 2805 | + } |
|
| 2806 | + |
|
| 2807 | + private function inCaption($token) { |
|
| 2808 | + /* An end tag whose tag name is "caption" */ |
|
| 2809 | + if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { |
|
| 2810 | + /* If the stack of open elements does not have an element in table |
|
| 2811 | 2811 | scope with the same tag name as the token, this is a parse error. |
| 2812 | 2812 | Ignore the token. (innerHTML case) */ |
| 2813 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 2814 | - // Ignore |
|
| 2813 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 2814 | + // Ignore |
|
| 2815 | 2815 | |
| 2816 | - /* Otherwise: */ |
|
| 2817 | - } else { |
|
| 2818 | - /* Generate implied end tags. */ |
|
| 2819 | - $this->generateImpliedEndTags(); |
|
| 2816 | + /* Otherwise: */ |
|
| 2817 | + } else { |
|
| 2818 | + /* Generate implied end tags. */ |
|
| 2819 | + $this->generateImpliedEndTags(); |
|
| 2820 | 2820 | |
| 2821 | - /* Now, if the current node is not a caption element, then this |
|
| 2821 | + /* Now, if the current node is not a caption element, then this |
|
| 2822 | 2822 | is a parse error. */ |
| 2823 | - // w/e |
|
| 2823 | + // w/e |
|
| 2824 | 2824 | |
| 2825 | - /* Pop elements from this stack until a caption element has |
|
| 2825 | + /* Pop elements from this stack until a caption element has |
|
| 2826 | 2826 | been popped from the stack. */ |
| 2827 | - while(true) { |
|
| 2828 | - $node = end($this->stack)->nodeName; |
|
| 2829 | - array_pop($this->stack); |
|
| 2827 | + while(true) { |
|
| 2828 | + $node = end($this->stack)->nodeName; |
|
| 2829 | + array_pop($this->stack); |
|
| 2830 | 2830 | |
| 2831 | - if($node === 'caption') { |
|
| 2832 | - break; |
|
| 2833 | - } |
|
| 2834 | - } |
|
| 2831 | + if($node === 'caption') { |
|
| 2832 | + break; |
|
| 2833 | + } |
|
| 2834 | + } |
|
| 2835 | 2835 | |
| 2836 | - /* Clear the list of active formatting elements up to the last |
|
| 2836 | + /* Clear the list of active formatting elements up to the last |
|
| 2837 | 2837 | marker. */ |
| 2838 | - $this->clearTheActiveFormattingElementsUpToTheLastMarker(); |
|
| 2838 | + $this->clearTheActiveFormattingElementsUpToTheLastMarker(); |
|
| 2839 | 2839 | |
| 2840 | - /* Switch the insertion mode to "in table". */ |
|
| 2841 | - $this->mode = self::IN_TABLE; |
|
| 2842 | - } |
|
| 2840 | + /* Switch the insertion mode to "in table". */ |
|
| 2841 | + $this->mode = self::IN_TABLE; |
|
| 2842 | + } |
|
| 2843 | 2843 | |
| 2844 | - /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 2844 | + /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 2845 | 2845 | "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag |
| 2846 | 2846 | name is "table" */ |
| 2847 | - } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2848 | - array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
|
| 2849 | - 'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG && |
|
| 2850 | - $token['name'] === 'table')) { |
|
| 2851 | - /* Parse error. Act as if an end tag with the tag name "caption" |
|
| 2847 | + } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2848 | + array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
|
| 2849 | + 'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG && |
|
| 2850 | + $token['name'] === 'table')) { |
|
| 2851 | + /* Parse error. Act as if an end tag with the tag name "caption" |
|
| 2852 | 2852 | had been seen, then, if that token wasn't ignored, reprocess the |
| 2853 | 2853 | current token. */ |
| 2854 | - $this->inCaption(array( |
|
| 2855 | - 'name' => 'caption', |
|
| 2856 | - 'type' => HTML5::ENDTAG |
|
| 2857 | - )); |
|
| 2854 | + $this->inCaption(array( |
|
| 2855 | + 'name' => 'caption', |
|
| 2856 | + 'type' => HTML5::ENDTAG |
|
| 2857 | + )); |
|
| 2858 | 2858 | |
| 2859 | - return $this->inTable($token); |
|
| 2859 | + return $this->inTable($token); |
|
| 2860 | 2860 | |
| 2861 | - /* An end tag whose tag name is one of: "body", "col", "colgroup", |
|
| 2861 | + /* An end tag whose tag name is one of: "body", "col", "colgroup", |
|
| 2862 | 2862 | "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 2863 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2864 | - array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th', |
|
| 2865 | - 'thead', 'tr'))) { |
|
| 2866 | - // Parse error. Ignore the token. |
|
| 2867 | - |
|
| 2868 | - /* Anything else */ |
|
| 2869 | - } else { |
|
| 2870 | - /* Process the token as if the insertion mode was "in body". */ |
|
| 2871 | - $this->inBody($token); |
|
| 2872 | - } |
|
| 2873 | - } |
|
| 2874 | - |
|
| 2875 | - private function inColumnGroup($token) { |
|
| 2876 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 2863 | + } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2864 | + array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th', |
|
| 2865 | + 'thead', 'tr'))) { |
|
| 2866 | + // Parse error. Ignore the token. |
|
| 2867 | + |
|
| 2868 | + /* Anything else */ |
|
| 2869 | + } else { |
|
| 2870 | + /* Process the token as if the insertion mode was "in body". */ |
|
| 2871 | + $this->inBody($token); |
|
| 2872 | + } |
|
| 2873 | + } |
|
| 2874 | + |
|
| 2875 | + private function inColumnGroup($token) { |
|
| 2876 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 2877 | 2877 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 2878 | 2878 | or U+0020 SPACE */ |
| 2879 | - if($token['type'] === HTML5::CHARACTR && |
|
| 2880 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 2881 | - /* Append the character to the current node. */ |
|
| 2882 | - $text = $this->dom->createTextNode($token['data']); |
|
| 2883 | - end($this->stack)->appendChild($text); |
|
| 2884 | - |
|
| 2885 | - /* A comment token */ |
|
| 2886 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 2887 | - /* Append a Comment node to the current node with the data |
|
| 2879 | + if($token['type'] === HTML5::CHARACTR && |
|
| 2880 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 2881 | + /* Append the character to the current node. */ |
|
| 2882 | + $text = $this->dom->createTextNode($token['data']); |
|
| 2883 | + end($this->stack)->appendChild($text); |
|
| 2884 | + |
|
| 2885 | + /* A comment token */ |
|
| 2886 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 2887 | + /* Append a Comment node to the current node with the data |
|
| 2888 | 2888 | attribute set to the data given in the comment token. */ |
| 2889 | - $comment = $this->dom->createComment($token['data']); |
|
| 2890 | - end($this->stack)->appendChild($comment); |
|
| 2889 | + $comment = $this->dom->createComment($token['data']); |
|
| 2890 | + end($this->stack)->appendChild($comment); |
|
| 2891 | 2891 | |
| 2892 | - /* A start tag whose tag name is "col" */ |
|
| 2893 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') { |
|
| 2894 | - /* Insert a col element for the token. Immediately pop the current |
|
| 2892 | + /* A start tag whose tag name is "col" */ |
|
| 2893 | + } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') { |
|
| 2894 | + /* Insert a col element for the token. Immediately pop the current |
|
| 2895 | 2895 | node off the stack of open elements. */ |
| 2896 | - $this->insertElement($token); |
|
| 2897 | - array_pop($this->stack); |
|
| 2896 | + $this->insertElement($token); |
|
| 2897 | + array_pop($this->stack); |
|
| 2898 | 2898 | |
| 2899 | - /* An end tag whose tag name is "colgroup" */ |
|
| 2900 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2901 | - $token['name'] === 'colgroup') { |
|
| 2902 | - /* If the current node is the root html element, then this is a |
|
| 2899 | + /* An end tag whose tag name is "colgroup" */ |
|
| 2900 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2901 | + $token['name'] === 'colgroup') { |
|
| 2902 | + /* If the current node is the root html element, then this is a |
|
| 2903 | 2903 | parse error, ignore the token. (innerHTML case) */ |
| 2904 | - if(end($this->stack)->nodeName === 'html') { |
|
| 2905 | - // Ignore |
|
| 2904 | + if(end($this->stack)->nodeName === 'html') { |
|
| 2905 | + // Ignore |
|
| 2906 | 2906 | |
| 2907 | - /* Otherwise, pop the current node (which will be a colgroup |
|
| 2907 | + /* Otherwise, pop the current node (which will be a colgroup |
|
| 2908 | 2908 | element) from the stack of open elements. Switch the insertion |
| 2909 | 2909 | mode to "in table". */ |
| 2910 | - } else { |
|
| 2911 | - array_pop($this->stack); |
|
| 2912 | - $this->mode = self::IN_TABLE; |
|
| 2913 | - } |
|
| 2914 | - |
|
| 2915 | - /* An end tag whose tag name is "col" */ |
|
| 2916 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { |
|
| 2917 | - /* Parse error. Ignore the token. */ |
|
| 2918 | - |
|
| 2919 | - /* Anything else */ |
|
| 2920 | - } else { |
|
| 2921 | - /* Act as if an end tag with the tag name "colgroup" had been seen, |
|
| 2910 | + } else { |
|
| 2911 | + array_pop($this->stack); |
|
| 2912 | + $this->mode = self::IN_TABLE; |
|
| 2913 | + } |
|
| 2914 | + |
|
| 2915 | + /* An end tag whose tag name is "col" */ |
|
| 2916 | + } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { |
|
| 2917 | + /* Parse error. Ignore the token. */ |
|
| 2918 | + |
|
| 2919 | + /* Anything else */ |
|
| 2920 | + } else { |
|
| 2921 | + /* Act as if an end tag with the tag name "colgroup" had been seen, |
|
| 2922 | 2922 | and then, if that token wasn't ignored, reprocess the current token. */ |
| 2923 | - $this->inColumnGroup(array( |
|
| 2924 | - 'name' => 'colgroup', |
|
| 2925 | - 'type' => HTML5::ENDTAG |
|
| 2926 | - )); |
|
| 2923 | + $this->inColumnGroup(array( |
|
| 2924 | + 'name' => 'colgroup', |
|
| 2925 | + 'type' => HTML5::ENDTAG |
|
| 2926 | + )); |
|
| 2927 | 2927 | |
| 2928 | - return $this->inTable($token); |
|
| 2929 | - } |
|
| 2930 | - } |
|
| 2928 | + return $this->inTable($token); |
|
| 2929 | + } |
|
| 2930 | + } |
|
| 2931 | 2931 | |
| 2932 | - private function inTableBody($token) { |
|
| 2933 | - $clear = array('tbody', 'tfoot', 'thead', 'html'); |
|
| 2932 | + private function inTableBody($token) { |
|
| 2933 | + $clear = array('tbody', 'tfoot', 'thead', 'html'); |
|
| 2934 | 2934 | |
| 2935 | - /* A start tag whose tag name is "tr" */ |
|
| 2936 | - if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { |
|
| 2937 | - /* Clear the stack back to a table body context. */ |
|
| 2938 | - $this->clearStackToTableContext($clear); |
|
| 2935 | + /* A start tag whose tag name is "tr" */ |
|
| 2936 | + if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { |
|
| 2937 | + /* Clear the stack back to a table body context. */ |
|
| 2938 | + $this->clearStackToTableContext($clear); |
|
| 2939 | 2939 | |
| 2940 | - /* Insert a tr element for the token, then switch the insertion |
|
| 2940 | + /* Insert a tr element for the token, then switch the insertion |
|
| 2941 | 2941 | mode to "in row". */ |
| 2942 | - $this->insertElement($token); |
|
| 2943 | - $this->mode = self::IN_ROW; |
|
| 2942 | + $this->insertElement($token); |
|
| 2943 | + $this->mode = self::IN_ROW; |
|
| 2944 | 2944 | |
| 2945 | - /* A start tag whose tag name is one of: "th", "td" */ |
|
| 2946 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2947 | - ($token['name'] === 'th' || $token['name'] === 'td')) { |
|
| 2948 | - /* Parse error. Act as if a start tag with the tag name "tr" had |
|
| 2945 | + /* A start tag whose tag name is one of: "th", "td" */ |
|
| 2946 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2947 | + ($token['name'] === 'th' || $token['name'] === 'td')) { |
|
| 2948 | + /* Parse error. Act as if a start tag with the tag name "tr" had |
|
| 2949 | 2949 | been seen, then reprocess the current token. */ |
| 2950 | - $this->inTableBody(array( |
|
| 2951 | - 'name' => 'tr', |
|
| 2952 | - 'type' => HTML5::STARTTAG, |
|
| 2953 | - 'attr' => array() |
|
| 2954 | - )); |
|
| 2955 | - |
|
| 2956 | - return $this->inRow($token); |
|
| 2957 | - |
|
| 2958 | - /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
|
| 2959 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2960 | - in_array($token['name'], array('tbody', 'tfoot', 'thead'))) { |
|
| 2961 | - /* If the stack of open elements does not have an element in table |
|
| 2950 | + $this->inTableBody(array( |
|
| 2951 | + 'name' => 'tr', |
|
| 2952 | + 'type' => HTML5::STARTTAG, |
|
| 2953 | + 'attr' => array() |
|
| 2954 | + )); |
|
| 2955 | + |
|
| 2956 | + return $this->inRow($token); |
|
| 2957 | + |
|
| 2958 | + /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
|
| 2959 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2960 | + in_array($token['name'], array('tbody', 'tfoot', 'thead'))) { |
|
| 2961 | + /* If the stack of open elements does not have an element in table |
|
| 2962 | 2962 | scope with the same tag name as the token, this is a parse error. |
| 2963 | 2963 | Ignore the token. */ |
| 2964 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 2965 | - // Ignore |
|
| 2964 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 2965 | + // Ignore |
|
| 2966 | 2966 | |
| 2967 | - /* Otherwise: */ |
|
| 2968 | - } else { |
|
| 2969 | - /* Clear the stack back to a table body context. */ |
|
| 2970 | - $this->clearStackToTableContext($clear); |
|
| 2967 | + /* Otherwise: */ |
|
| 2968 | + } else { |
|
| 2969 | + /* Clear the stack back to a table body context. */ |
|
| 2970 | + $this->clearStackToTableContext($clear); |
|
| 2971 | 2971 | |
| 2972 | - /* Pop the current node from the stack of open elements. Switch |
|
| 2972 | + /* Pop the current node from the stack of open elements. Switch |
|
| 2973 | 2973 | the insertion mode to "in table". */ |
| 2974 | - array_pop($this->stack); |
|
| 2975 | - $this->mode = self::IN_TABLE; |
|
| 2976 | - } |
|
| 2974 | + array_pop($this->stack); |
|
| 2975 | + $this->mode = self::IN_TABLE; |
|
| 2976 | + } |
|
| 2977 | 2977 | |
| 2978 | - /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 2978 | + /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 2979 | 2979 | "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */ |
| 2980 | - } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2981 | - array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) || |
|
| 2982 | - ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) { |
|
| 2983 | - /* If the stack of open elements does not have a tbody, thead, or |
|
| 2980 | + } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2981 | + array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) || |
|
| 2982 | + ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) { |
|
| 2983 | + /* If the stack of open elements does not have a tbody, thead, or |
|
| 2984 | 2984 | tfoot element in table scope, this is a parse error. Ignore the |
| 2985 | 2985 | token. (innerHTML case) */ |
| 2986 | - if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { |
|
| 2987 | - // Ignore. |
|
| 2986 | + if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { |
|
| 2987 | + // Ignore. |
|
| 2988 | 2988 | |
| 2989 | - /* Otherwise: */ |
|
| 2990 | - } else { |
|
| 2991 | - /* Clear the stack back to a table body context. */ |
|
| 2992 | - $this->clearStackToTableContext($clear); |
|
| 2989 | + /* Otherwise: */ |
|
| 2990 | + } else { |
|
| 2991 | + /* Clear the stack back to a table body context. */ |
|
| 2992 | + $this->clearStackToTableContext($clear); |
|
| 2993 | 2993 | |
| 2994 | - /* Act as if an end tag with the same tag name as the current |
|
| 2994 | + /* Act as if an end tag with the same tag name as the current |
|
| 2995 | 2995 | node ("tbody", "tfoot", or "thead") had been seen, then |
| 2996 | 2996 | reprocess the current token. */ |
| 2997 | - $this->inTableBody(array( |
|
| 2998 | - 'name' => end($this->stack)->nodeName, |
|
| 2999 | - 'type' => HTML5::ENDTAG |
|
| 3000 | - )); |
|
| 2997 | + $this->inTableBody(array( |
|
| 2998 | + 'name' => end($this->stack)->nodeName, |
|
| 2999 | + 'type' => HTML5::ENDTAG |
|
| 3000 | + )); |
|
| 3001 | 3001 | |
| 3002 | - return $this->mainPhase($token); |
|
| 3003 | - } |
|
| 3002 | + return $this->mainPhase($token); |
|
| 3003 | + } |
|
| 3004 | 3004 | |
| 3005 | - /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 3005 | + /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 3006 | 3006 | "colgroup", "html", "td", "th", "tr" */ |
| 3007 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3008 | - array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) { |
|
| 3009 | - /* Parse error. Ignore the token. */ |
|
| 3010 | - |
|
| 3011 | - /* Anything else */ |
|
| 3012 | - } else { |
|
| 3013 | - /* Process the token as if the insertion mode was "in table". */ |
|
| 3014 | - $this->inTable($token); |
|
| 3015 | - } |
|
| 3016 | - } |
|
| 3017 | - |
|
| 3018 | - private function inRow($token) { |
|
| 3019 | - $clear = array('tr', 'html'); |
|
| 3020 | - |
|
| 3021 | - /* A start tag whose tag name is one of: "th", "td" */ |
|
| 3022 | - if($token['type'] === HTML5::STARTTAG && |
|
| 3023 | - ($token['name'] === 'th' || $token['name'] === 'td')) { |
|
| 3024 | - /* Clear the stack back to a table row context. */ |
|
| 3025 | - $this->clearStackToTableContext($clear); |
|
| 3026 | - |
|
| 3027 | - /* Insert an HTML element for the token, then switch the insertion |
|
| 3007 | + } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3008 | + array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) { |
|
| 3009 | + /* Parse error. Ignore the token. */ |
|
| 3010 | + |
|
| 3011 | + /* Anything else */ |
|
| 3012 | + } else { |
|
| 3013 | + /* Process the token as if the insertion mode was "in table". */ |
|
| 3014 | + $this->inTable($token); |
|
| 3015 | + } |
|
| 3016 | + } |
|
| 3017 | + |
|
| 3018 | + private function inRow($token) { |
|
| 3019 | + $clear = array('tr', 'html'); |
|
| 3020 | + |
|
| 3021 | + /* A start tag whose tag name is one of: "th", "td" */ |
|
| 3022 | + if($token['type'] === HTML5::STARTTAG && |
|
| 3023 | + ($token['name'] === 'th' || $token['name'] === 'td')) { |
|
| 3024 | + /* Clear the stack back to a table row context. */ |
|
| 3025 | + $this->clearStackToTableContext($clear); |
|
| 3026 | + |
|
| 3027 | + /* Insert an HTML element for the token, then switch the insertion |
|
| 3028 | 3028 | mode to "in cell". */ |
| 3029 | - $this->insertElement($token); |
|
| 3030 | - $this->mode = self::IN_CELL; |
|
| 3029 | + $this->insertElement($token); |
|
| 3030 | + $this->mode = self::IN_CELL; |
|
| 3031 | 3031 | |
| 3032 | - /* Insert a marker at the end of the list of active formatting |
|
| 3032 | + /* Insert a marker at the end of the list of active formatting |
|
| 3033 | 3033 | elements. */ |
| 3034 | - $this->a_formatting[] = self::MARKER; |
|
| 3034 | + $this->a_formatting[] = self::MARKER; |
|
| 3035 | 3035 | |
| 3036 | - /* An end tag whose tag name is "tr" */ |
|
| 3037 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { |
|
| 3038 | - /* If the stack of open elements does not have an element in table |
|
| 3036 | + /* An end tag whose tag name is "tr" */ |
|
| 3037 | + } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { |
|
| 3038 | + /* If the stack of open elements does not have an element in table |
|
| 3039 | 3039 | scope with the same tag name as the token, this is a parse error. |
| 3040 | 3040 | Ignore the token. (innerHTML case) */ |
| 3041 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3042 | - // Ignore. |
|
| 3041 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 3042 | + // Ignore. |
|
| 3043 | 3043 | |
| 3044 | - /* Otherwise: */ |
|
| 3045 | - } else { |
|
| 3046 | - /* Clear the stack back to a table row context. */ |
|
| 3047 | - $this->clearStackToTableContext($clear); |
|
| 3044 | + /* Otherwise: */ |
|
| 3045 | + } else { |
|
| 3046 | + /* Clear the stack back to a table row context. */ |
|
| 3047 | + $this->clearStackToTableContext($clear); |
|
| 3048 | 3048 | |
| 3049 | - /* Pop the current node (which will be a tr element) from the |
|
| 3049 | + /* Pop the current node (which will be a tr element) from the |
|
| 3050 | 3050 | stack of open elements. Switch the insertion mode to "in table |
| 3051 | 3051 | body". */ |
| 3052 | - array_pop($this->stack); |
|
| 3053 | - $this->mode = self::IN_TBODY; |
|
| 3054 | - } |
|
| 3052 | + array_pop($this->stack); |
|
| 3053 | + $this->mode = self::IN_TBODY; |
|
| 3054 | + } |
|
| 3055 | 3055 | |
| 3056 | - /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 3056 | + /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 3057 | 3057 | "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */ |
| 3058 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3059 | - array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) { |
|
| 3060 | - /* Act as if an end tag with the tag name "tr" had been seen, then, |
|
| 3058 | + } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3059 | + array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) { |
|
| 3060 | + /* Act as if an end tag with the tag name "tr" had been seen, then, |
|
| 3061 | 3061 | if that token wasn't ignored, reprocess the current token. */ |
| 3062 | - $this->inRow(array( |
|
| 3063 | - 'name' => 'tr', |
|
| 3064 | - 'type' => HTML5::ENDTAG |
|
| 3065 | - )); |
|
| 3062 | + $this->inRow(array( |
|
| 3063 | + 'name' => 'tr', |
|
| 3064 | + 'type' => HTML5::ENDTAG |
|
| 3065 | + )); |
|
| 3066 | 3066 | |
| 3067 | - return $this->inCell($token); |
|
| 3067 | + return $this->inCell($token); |
|
| 3068 | 3068 | |
| 3069 | - /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
|
| 3070 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3071 | - in_array($token['name'], array('tbody', 'tfoot', 'thead'))) { |
|
| 3072 | - /* If the stack of open elements does not have an element in table |
|
| 3069 | + /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
|
| 3070 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3071 | + in_array($token['name'], array('tbody', 'tfoot', 'thead'))) { |
|
| 3072 | + /* If the stack of open elements does not have an element in table |
|
| 3073 | 3073 | scope with the same tag name as the token, this is a parse error. |
| 3074 | 3074 | Ignore the token. */ |
| 3075 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3076 | - // Ignore. |
|
| 3075 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 3076 | + // Ignore. |
|
| 3077 | 3077 | |
| 3078 | - /* Otherwise: */ |
|
| 3079 | - } else { |
|
| 3080 | - /* Otherwise, act as if an end tag with the tag name "tr" had |
|
| 3078 | + /* Otherwise: */ |
|
| 3079 | + } else { |
|
| 3080 | + /* Otherwise, act as if an end tag with the tag name "tr" had |
|
| 3081 | 3081 | been seen, then reprocess the current token. */ |
| 3082 | - $this->inRow(array( |
|
| 3083 | - 'name' => 'tr', |
|
| 3084 | - 'type' => HTML5::ENDTAG |
|
| 3085 | - )); |
|
| 3082 | + $this->inRow(array( |
|
| 3083 | + 'name' => 'tr', |
|
| 3084 | + 'type' => HTML5::ENDTAG |
|
| 3085 | + )); |
|
| 3086 | 3086 | |
| 3087 | - return $this->inCell($token); |
|
| 3088 | - } |
|
| 3087 | + return $this->inCell($token); |
|
| 3088 | + } |
|
| 3089 | 3089 | |
| 3090 | - /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 3090 | + /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 3091 | 3091 | "colgroup", "html", "td", "th" */ |
| 3092 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3093 | - array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) { |
|
| 3094 | - /* Parse error. Ignore the token. */ |
|
| 3095 | - |
|
| 3096 | - /* Anything else */ |
|
| 3097 | - } else { |
|
| 3098 | - /* Process the token as if the insertion mode was "in table". */ |
|
| 3099 | - $this->inTable($token); |
|
| 3100 | - } |
|
| 3101 | - } |
|
| 3102 | - |
|
| 3103 | - private function inCell($token) { |
|
| 3104 | - /* An end tag whose tag name is one of: "td", "th" */ |
|
| 3105 | - if($token['type'] === HTML5::ENDTAG && |
|
| 3106 | - ($token['name'] === 'td' || $token['name'] === 'th')) { |
|
| 3107 | - /* If the stack of open elements does not have an element in table |
|
| 3092 | + } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3093 | + array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) { |
|
| 3094 | + /* Parse error. Ignore the token. */ |
|
| 3095 | + |
|
| 3096 | + /* Anything else */ |
|
| 3097 | + } else { |
|
| 3098 | + /* Process the token as if the insertion mode was "in table". */ |
|
| 3099 | + $this->inTable($token); |
|
| 3100 | + } |
|
| 3101 | + } |
|
| 3102 | + |
|
| 3103 | + private function inCell($token) { |
|
| 3104 | + /* An end tag whose tag name is one of: "td", "th" */ |
|
| 3105 | + if($token['type'] === HTML5::ENDTAG && |
|
| 3106 | + ($token['name'] === 'td' || $token['name'] === 'th')) { |
|
| 3107 | + /* If the stack of open elements does not have an element in table |
|
| 3108 | 3108 | scope with the same tag name as that of the token, then this is a |
| 3109 | 3109 | parse error and the token must be ignored. */ |
| 3110 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3111 | - // Ignore. |
|
| 3110 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 3111 | + // Ignore. |
|
| 3112 | 3112 | |
| 3113 | - /* Otherwise: */ |
|
| 3114 | - } else { |
|
| 3115 | - /* Generate implied end tags, except for elements with the same |
|
| 3113 | + /* Otherwise: */ |
|
| 3114 | + } else { |
|
| 3115 | + /* Generate implied end tags, except for elements with the same |
|
| 3116 | 3116 | tag name as the token. */ |
| 3117 | - $this->generateImpliedEndTags(array($token['name'])); |
|
| 3117 | + $this->generateImpliedEndTags(array($token['name'])); |
|
| 3118 | 3118 | |
| 3119 | - /* Now, if the current node is not an element with the same tag |
|
| 3119 | + /* Now, if the current node is not an element with the same tag |
|
| 3120 | 3120 | name as the token, then this is a parse error. */ |
| 3121 | - // k |
|
| 3121 | + // k |
|
| 3122 | 3122 | |
| 3123 | - /* Pop elements from this stack until an element with the same |
|
| 3123 | + /* Pop elements from this stack until an element with the same |
|
| 3124 | 3124 | tag name as the token has been popped from the stack. */ |
| 3125 | - while(true) { |
|
| 3126 | - $node = end($this->stack)->nodeName; |
|
| 3127 | - array_pop($this->stack); |
|
| 3125 | + while(true) { |
|
| 3126 | + $node = end($this->stack)->nodeName; |
|
| 3127 | + array_pop($this->stack); |
|
| 3128 | 3128 | |
| 3129 | - if($node === $token['name']) { |
|
| 3130 | - break; |
|
| 3131 | - } |
|
| 3132 | - } |
|
| 3129 | + if($node === $token['name']) { |
|
| 3130 | + break; |
|
| 3131 | + } |
|
| 3132 | + } |
|
| 3133 | 3133 | |
| 3134 | - /* Clear the list of active formatting elements up to the last |
|
| 3134 | + /* Clear the list of active formatting elements up to the last |
|
| 3135 | 3135 | marker. */ |
| 3136 | - $this->clearTheActiveFormattingElementsUpToTheLastMarker(); |
|
| 3136 | + $this->clearTheActiveFormattingElementsUpToTheLastMarker(); |
|
| 3137 | 3137 | |
| 3138 | - /* Switch the insertion mode to "in row". (The current node |
|
| 3138 | + /* Switch the insertion mode to "in row". (The current node |
|
| 3139 | 3139 | will be a tr element at this point.) */ |
| 3140 | - $this->mode = self::IN_ROW; |
|
| 3141 | - } |
|
| 3140 | + $this->mode = self::IN_ROW; |
|
| 3141 | + } |
|
| 3142 | 3142 | |
| 3143 | - /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 3143 | + /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 3144 | 3144 | "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 3145 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3146 | - array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
|
| 3147 | - 'thead', 'tr'))) { |
|
| 3148 | - /* If the stack of open elements does not have a td or th element |
|
| 3145 | + } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3146 | + array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
|
| 3147 | + 'thead', 'tr'))) { |
|
| 3148 | + /* If the stack of open elements does not have a td or th element |
|
| 3149 | 3149 | in table scope, then this is a parse error; ignore the token. |
| 3150 | 3150 | (innerHTML case) */ |
| 3151 | - if(!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3152 | - // Ignore. |
|
| 3151 | + if(!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3152 | + // Ignore. |
|
| 3153 | 3153 | |
| 3154 | - /* Otherwise, close the cell (see below) and reprocess the current |
|
| 3154 | + /* Otherwise, close the cell (see below) and reprocess the current |
|
| 3155 | 3155 | token. */ |
| 3156 | - } else { |
|
| 3157 | - $this->closeCell(); |
|
| 3158 | - return $this->inRow($token); |
|
| 3159 | - } |
|
| 3156 | + } else { |
|
| 3157 | + $this->closeCell(); |
|
| 3158 | + return $this->inRow($token); |
|
| 3159 | + } |
|
| 3160 | 3160 | |
| 3161 | - /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 3161 | + /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
|
| 3162 | 3162 | "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 3163 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3164 | - array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
|
| 3165 | - 'thead', 'tr'))) { |
|
| 3166 | - /* If the stack of open elements does not have a td or th element |
|
| 3163 | + } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3164 | + array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
|
| 3165 | + 'thead', 'tr'))) { |
|
| 3166 | + /* If the stack of open elements does not have a td or th element |
|
| 3167 | 3167 | in table scope, then this is a parse error; ignore the token. |
| 3168 | 3168 | (innerHTML case) */ |
| 3169 | - if(!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3170 | - // Ignore. |
|
| 3169 | + if(!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3170 | + // Ignore. |
|
| 3171 | 3171 | |
| 3172 | - /* Otherwise, close the cell (see below) and reprocess the current |
|
| 3172 | + /* Otherwise, close the cell (see below) and reprocess the current |
|
| 3173 | 3173 | token. */ |
| 3174 | - } else { |
|
| 3175 | - $this->closeCell(); |
|
| 3176 | - return $this->inRow($token); |
|
| 3177 | - } |
|
| 3174 | + } else { |
|
| 3175 | + $this->closeCell(); |
|
| 3176 | + return $this->inRow($token); |
|
| 3177 | + } |
|
| 3178 | 3178 | |
| 3179 | - /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 3179 | + /* An end tag whose tag name is one of: "body", "caption", "col", |
|
| 3180 | 3180 | "colgroup", "html" */ |
| 3181 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3182 | - array('body', 'caption', 'col', 'colgroup', 'html'))) { |
|
| 3183 | - /* Parse error. Ignore the token. */ |
|
| 3181 | + } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3182 | + array('body', 'caption', 'col', 'colgroup', 'html'))) { |
|
| 3183 | + /* Parse error. Ignore the token. */ |
|
| 3184 | 3184 | |
| 3185 | - /* An end tag whose tag name is one of: "table", "tbody", "tfoot", |
|
| 3185 | + /* An end tag whose tag name is one of: "table", "tbody", "tfoot", |
|
| 3186 | 3186 | "thead", "tr" */ |
| 3187 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3188 | - array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { |
|
| 3189 | - /* If the stack of open elements does not have an element in table |
|
| 3187 | + } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3188 | + array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { |
|
| 3189 | + /* If the stack of open elements does not have an element in table |
|
| 3190 | 3190 | scope with the same tag name as that of the token (which can only |
| 3191 | 3191 | happen for "tbody", "tfoot" and "thead", or, in the innerHTML case), |
| 3192 | 3192 | then this is a parse error and the token must be ignored. */ |
| 3193 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3194 | - // Ignore. |
|
| 3193 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 3194 | + // Ignore. |
|
| 3195 | 3195 | |
| 3196 | - /* Otherwise, close the cell (see below) and reprocess the current |
|
| 3196 | + /* Otherwise, close the cell (see below) and reprocess the current |
|
| 3197 | 3197 | token. */ |
| 3198 | - } else { |
|
| 3199 | - $this->closeCell(); |
|
| 3200 | - return $this->inRow($token); |
|
| 3201 | - } |
|
| 3202 | - |
|
| 3203 | - /* Anything else */ |
|
| 3204 | - } else { |
|
| 3205 | - /* Process the token as if the insertion mode was "in body". */ |
|
| 3206 | - $this->inBody($token); |
|
| 3207 | - } |
|
| 3208 | - } |
|
| 3209 | - |
|
| 3210 | - private function inSelect($token) { |
|
| 3211 | - /* Handle the token as follows: */ |
|
| 3212 | - |
|
| 3213 | - /* A character token */ |
|
| 3214 | - if($token['type'] === HTML5::CHARACTR) { |
|
| 3215 | - /* Append the token's character to the current node. */ |
|
| 3216 | - $this->insertText($token['data']); |
|
| 3217 | - |
|
| 3218 | - /* A comment token */ |
|
| 3219 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3220 | - /* Append a Comment node to the current node with the data |
|
| 3198 | + } else { |
|
| 3199 | + $this->closeCell(); |
|
| 3200 | + return $this->inRow($token); |
|
| 3201 | + } |
|
| 3202 | + |
|
| 3203 | + /* Anything else */ |
|
| 3204 | + } else { |
|
| 3205 | + /* Process the token as if the insertion mode was "in body". */ |
|
| 3206 | + $this->inBody($token); |
|
| 3207 | + } |
|
| 3208 | + } |
|
| 3209 | + |
|
| 3210 | + private function inSelect($token) { |
|
| 3211 | + /* Handle the token as follows: */ |
|
| 3212 | + |
|
| 3213 | + /* A character token */ |
|
| 3214 | + if($token['type'] === HTML5::CHARACTR) { |
|
| 3215 | + /* Append the token's character to the current node. */ |
|
| 3216 | + $this->insertText($token['data']); |
|
| 3217 | + |
|
| 3218 | + /* A comment token */ |
|
| 3219 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3220 | + /* Append a Comment node to the current node with the data |
|
| 3221 | 3221 | attribute set to the data given in the comment token. */ |
| 3222 | - $this->insertComment($token['data']); |
|
| 3222 | + $this->insertComment($token['data']); |
|
| 3223 | 3223 | |
| 3224 | - /* A start tag token whose tag name is "option" */ |
|
| 3225 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 3226 | - $token['name'] === 'option') { |
|
| 3227 | - /* If the current node is an option element, act as if an end tag |
|
| 3224 | + /* A start tag token whose tag name is "option" */ |
|
| 3225 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 3226 | + $token['name'] === 'option') { |
|
| 3227 | + /* If the current node is an option element, act as if an end tag |
|
| 3228 | 3228 | with the tag name "option" had been seen. */ |
| 3229 | - if(end($this->stack)->nodeName === 'option') { |
|
| 3230 | - $this->inSelect(array( |
|
| 3231 | - 'name' => 'option', |
|
| 3232 | - 'type' => HTML5::ENDTAG |
|
| 3233 | - )); |
|
| 3234 | - } |
|
| 3235 | - |
|
| 3236 | - /* Insert an HTML element for the token. */ |
|
| 3237 | - $this->insertElement($token); |
|
| 3238 | - |
|
| 3239 | - /* A start tag token whose tag name is "optgroup" */ |
|
| 3240 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 3241 | - $token['name'] === 'optgroup') { |
|
| 3242 | - /* If the current node is an option element, act as if an end tag |
|
| 3229 | + if(end($this->stack)->nodeName === 'option') { |
|
| 3230 | + $this->inSelect(array( |
|
| 3231 | + 'name' => 'option', |
|
| 3232 | + 'type' => HTML5::ENDTAG |
|
| 3233 | + )); |
|
| 3234 | + } |
|
| 3235 | + |
|
| 3236 | + /* Insert an HTML element for the token. */ |
|
| 3237 | + $this->insertElement($token); |
|
| 3238 | + |
|
| 3239 | + /* A start tag token whose tag name is "optgroup" */ |
|
| 3240 | + } elseif($token['type'] === HTML5::STARTTAG && |
|
| 3241 | + $token['name'] === 'optgroup') { |
|
| 3242 | + /* If the current node is an option element, act as if an end tag |
|
| 3243 | 3243 | with the tag name "option" had been seen. */ |
| 3244 | - if(end($this->stack)->nodeName === 'option') { |
|
| 3245 | - $this->inSelect(array( |
|
| 3246 | - 'name' => 'option', |
|
| 3247 | - 'type' => HTML5::ENDTAG |
|
| 3248 | - )); |
|
| 3249 | - } |
|
| 3250 | - |
|
| 3251 | - /* If the current node is an optgroup element, act as if an end tag |
|
| 3244 | + if(end($this->stack)->nodeName === 'option') { |
|
| 3245 | + $this->inSelect(array( |
|
| 3246 | + 'name' => 'option', |
|
| 3247 | + 'type' => HTML5::ENDTAG |
|
| 3248 | + )); |
|
| 3249 | + } |
|
| 3250 | + |
|
| 3251 | + /* If the current node is an optgroup element, act as if an end tag |
|
| 3252 | 3252 | with the tag name "optgroup" had been seen. */ |
| 3253 | - if(end($this->stack)->nodeName === 'optgroup') { |
|
| 3254 | - $this->inSelect(array( |
|
| 3255 | - 'name' => 'optgroup', |
|
| 3256 | - 'type' => HTML5::ENDTAG |
|
| 3257 | - )); |
|
| 3258 | - } |
|
| 3259 | - |
|
| 3260 | - /* Insert an HTML element for the token. */ |
|
| 3261 | - $this->insertElement($token); |
|
| 3262 | - |
|
| 3263 | - /* An end tag token whose tag name is "optgroup" */ |
|
| 3264 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3265 | - $token['name'] === 'optgroup') { |
|
| 3266 | - /* First, if the current node is an option element, and the node |
|
| 3253 | + if(end($this->stack)->nodeName === 'optgroup') { |
|
| 3254 | + $this->inSelect(array( |
|
| 3255 | + 'name' => 'optgroup', |
|
| 3256 | + 'type' => HTML5::ENDTAG |
|
| 3257 | + )); |
|
| 3258 | + } |
|
| 3259 | + |
|
| 3260 | + /* Insert an HTML element for the token. */ |
|
| 3261 | + $this->insertElement($token); |
|
| 3262 | + |
|
| 3263 | + /* An end tag token whose tag name is "optgroup" */ |
|
| 3264 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3265 | + $token['name'] === 'optgroup') { |
|
| 3266 | + /* First, if the current node is an option element, and the node |
|
| 3267 | 3267 | immediately before it in the stack of open elements is an optgroup |
| 3268 | 3268 | element, then act as if an end tag with the tag name "option" had |
| 3269 | 3269 | been seen. */ |
| 3270 | - $elements_in_stack = count($this->stack); |
|
| 3270 | + $elements_in_stack = count($this->stack); |
|
| 3271 | 3271 | |
| 3272 | - if($this->stack[$elements_in_stack - 1]->nodeName === 'option' && |
|
| 3273 | - $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') { |
|
| 3274 | - $this->inSelect(array( |
|
| 3275 | - 'name' => 'option', |
|
| 3276 | - 'type' => HTML5::ENDTAG |
|
| 3277 | - )); |
|
| 3278 | - } |
|
| 3272 | + if($this->stack[$elements_in_stack - 1]->nodeName === 'option' && |
|
| 3273 | + $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') { |
|
| 3274 | + $this->inSelect(array( |
|
| 3275 | + 'name' => 'option', |
|
| 3276 | + 'type' => HTML5::ENDTAG |
|
| 3277 | + )); |
|
| 3278 | + } |
|
| 3279 | 3279 | |
| 3280 | - /* If the current node is an optgroup element, then pop that node |
|
| 3280 | + /* If the current node is an optgroup element, then pop that node |
|
| 3281 | 3281 | from the stack of open elements. Otherwise, this is a parse error, |
| 3282 | 3282 | ignore the token. */ |
| 3283 | - if($this->stack[$elements_in_stack - 1] === 'optgroup') { |
|
| 3284 | - array_pop($this->stack); |
|
| 3285 | - } |
|
| 3286 | - |
|
| 3287 | - /* An end tag token whose tag name is "option" */ |
|
| 3288 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3289 | - $token['name'] === 'option') { |
|
| 3290 | - /* If the current node is an option element, then pop that node |
|
| 3283 | + if($this->stack[$elements_in_stack - 1] === 'optgroup') { |
|
| 3284 | + array_pop($this->stack); |
|
| 3285 | + } |
|
| 3286 | + |
|
| 3287 | + /* An end tag token whose tag name is "option" */ |
|
| 3288 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3289 | + $token['name'] === 'option') { |
|
| 3290 | + /* If the current node is an option element, then pop that node |
|
| 3291 | 3291 | from the stack of open elements. Otherwise, this is a parse error, |
| 3292 | 3292 | ignore the token. */ |
| 3293 | - if(end($this->stack)->nodeName === 'option') { |
|
| 3294 | - array_pop($this->stack); |
|
| 3295 | - } |
|
| 3296 | - |
|
| 3297 | - /* An end tag whose tag name is "select" */ |
|
| 3298 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3299 | - $token['name'] === 'select') { |
|
| 3300 | - /* If the stack of open elements does not have an element in table |
|
| 3293 | + if(end($this->stack)->nodeName === 'option') { |
|
| 3294 | + array_pop($this->stack); |
|
| 3295 | + } |
|
| 3296 | + |
|
| 3297 | + /* An end tag whose tag name is "select" */ |
|
| 3298 | + } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3299 | + $token['name'] === 'select') { |
|
| 3300 | + /* If the stack of open elements does not have an element in table |
|
| 3301 | 3301 | scope with the same tag name as the token, this is a parse error. |
| 3302 | 3302 | Ignore the token. (innerHTML case) */ |
| 3303 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3304 | - // w/e |
|
| 3303 | + if(!$this->elementInScope($token['name'], true)) { |
|
| 3304 | + // w/e |
|
| 3305 | 3305 | |
| 3306 | - /* Otherwise: */ |
|
| 3307 | - } else { |
|
| 3308 | - /* Pop elements from the stack of open elements until a select |
|
| 3306 | + /* Otherwise: */ |
|
| 3307 | + } else { |
|
| 3308 | + /* Pop elements from the stack of open elements until a select |
|
| 3309 | 3309 | element has been popped from the stack. */ |
| 3310 | - while(true) { |
|
| 3311 | - $current = end($this->stack)->nodeName; |
|
| 3312 | - array_pop($this->stack); |
|
| 3313 | - |
|
| 3314 | - if($current === 'select') { |
|
| 3315 | - break; |
|
| 3316 | - } |
|
| 3317 | - } |
|
| 3318 | - |
|
| 3319 | - /* Reset the insertion mode appropriately. */ |
|
| 3320 | - $this->resetInsertionMode(); |
|
| 3321 | - } |
|
| 3322 | - |
|
| 3323 | - /* A start tag whose tag name is "select" */ |
|
| 3324 | - } elseif($token['name'] === 'select' && |
|
| 3325 | - $token['type'] === HTML5::STARTTAG) { |
|
| 3326 | - /* Parse error. Act as if the token had been an end tag with the |
|
| 3310 | + while(true) { |
|
| 3311 | + $current = end($this->stack)->nodeName; |
|
| 3312 | + array_pop($this->stack); |
|
| 3313 | + |
|
| 3314 | + if($current === 'select') { |
|
| 3315 | + break; |
|
| 3316 | + } |
|
| 3317 | + } |
|
| 3318 | + |
|
| 3319 | + /* Reset the insertion mode appropriately. */ |
|
| 3320 | + $this->resetInsertionMode(); |
|
| 3321 | + } |
|
| 3322 | + |
|
| 3323 | + /* A start tag whose tag name is "select" */ |
|
| 3324 | + } elseif($token['name'] === 'select' && |
|
| 3325 | + $token['type'] === HTML5::STARTTAG) { |
|
| 3326 | + /* Parse error. Act as if the token had been an end tag with the |
|
| 3327 | 3327 | tag name "select" instead. */ |
| 3328 | - $this->inSelect(array( |
|
| 3329 | - 'name' => 'select', |
|
| 3330 | - 'type' => HTML5::ENDTAG |
|
| 3331 | - )); |
|
| 3328 | + $this->inSelect(array( |
|
| 3329 | + 'name' => 'select', |
|
| 3330 | + 'type' => HTML5::ENDTAG |
|
| 3331 | + )); |
|
| 3332 | 3332 | |
| 3333 | - /* An end tag whose tag name is one of: "caption", "table", "tbody", |
|
| 3333 | + /* An end tag whose tag name is one of: "caption", "table", "tbody", |
|
| 3334 | 3334 | "tfoot", "thead", "tr", "td", "th" */ |
| 3335 | - } elseif(in_array($token['name'], array('caption', 'table', 'tbody', |
|
| 3336 | - 'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) { |
|
| 3337 | - /* Parse error. */ |
|
| 3338 | - // w/e |
|
| 3335 | + } elseif(in_array($token['name'], array('caption', 'table', 'tbody', |
|
| 3336 | + 'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) { |
|
| 3337 | + /* Parse error. */ |
|
| 3338 | + // w/e |
|
| 3339 | 3339 | |
| 3340 | - /* If the stack of open elements has an element in table scope with |
|
| 3340 | + /* If the stack of open elements has an element in table scope with |
|
| 3341 | 3341 | the same tag name as that of the token, then act as if an end tag |
| 3342 | 3342 | with the tag name "select" had been seen, and reprocess the token. |
| 3343 | 3343 | Otherwise, ignore the token. */ |
| 3344 | - if($this->elementInScope($token['name'], true)) { |
|
| 3345 | - $this->inSelect(array( |
|
| 3346 | - 'name' => 'select', |
|
| 3347 | - 'type' => HTML5::ENDTAG |
|
| 3348 | - )); |
|
| 3344 | + if($this->elementInScope($token['name'], true)) { |
|
| 3345 | + $this->inSelect(array( |
|
| 3346 | + 'name' => 'select', |
|
| 3347 | + 'type' => HTML5::ENDTAG |
|
| 3348 | + )); |
|
| 3349 | 3349 | |
| 3350 | - $this->mainPhase($token); |
|
| 3351 | - } |
|
| 3350 | + $this->mainPhase($token); |
|
| 3351 | + } |
|
| 3352 | 3352 | |
| 3353 | - /* Anything else */ |
|
| 3354 | - } else { |
|
| 3355 | - /* Parse error. Ignore the token. */ |
|
| 3356 | - } |
|
| 3357 | - } |
|
| 3353 | + /* Anything else */ |
|
| 3354 | + } else { |
|
| 3355 | + /* Parse error. Ignore the token. */ |
|
| 3356 | + } |
|
| 3357 | + } |
|
| 3358 | 3358 | |
| 3359 | - private function afterBody($token) { |
|
| 3360 | - /* Handle the token as follows: */ |
|
| 3359 | + private function afterBody($token) { |
|
| 3360 | + /* Handle the token as follows: */ |
|
| 3361 | 3361 | |
| 3362 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3362 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3363 | 3363 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3364 | 3364 | or U+0020 SPACE */ |
| 3365 | - if($token['type'] === HTML5::CHARACTR && |
|
| 3366 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3367 | - /* Process the token as it would be processed if the insertion mode |
|
| 3365 | + if($token['type'] === HTML5::CHARACTR && |
|
| 3366 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3367 | + /* Process the token as it would be processed if the insertion mode |
|
| 3368 | 3368 | was "in body". */ |
| 3369 | - $this->inBody($token); |
|
| 3369 | + $this->inBody($token); |
|
| 3370 | 3370 | |
| 3371 | - /* A comment token */ |
|
| 3372 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3373 | - /* Append a Comment node to the first element in the stack of open |
|
| 3371 | + /* A comment token */ |
|
| 3372 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3373 | + /* Append a Comment node to the first element in the stack of open |
|
| 3374 | 3374 | elements (the html element), with the data attribute set to the |
| 3375 | 3375 | data given in the comment token. */ |
| 3376 | - $comment = $this->dom->createComment($token['data']); |
|
| 3377 | - $this->stack[0]->appendChild($comment); |
|
| 3376 | + $comment = $this->dom->createComment($token['data']); |
|
| 3377 | + $this->stack[0]->appendChild($comment); |
|
| 3378 | 3378 | |
| 3379 | - /* An end tag with the tag name "html" */ |
|
| 3380 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') { |
|
| 3381 | - /* If the parser was originally created in order to handle the |
|
| 3379 | + /* An end tag with the tag name "html" */ |
|
| 3380 | + } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') { |
|
| 3381 | + /* If the parser was originally created in order to handle the |
|
| 3382 | 3382 | setting of an element's innerHTML attribute, this is a parse error; |
| 3383 | 3383 | ignore the token. (The element will be an html element in this |
| 3384 | 3384 | case.) (innerHTML case) */ |
| 3385 | 3385 | |
| 3386 | - /* Otherwise, switch to the trailing end phase. */ |
|
| 3387 | - $this->phase = self::END_PHASE; |
|
| 3386 | + /* Otherwise, switch to the trailing end phase. */ |
|
| 3387 | + $this->phase = self::END_PHASE; |
|
| 3388 | 3388 | |
| 3389 | - /* Anything else */ |
|
| 3390 | - } else { |
|
| 3391 | - /* Parse error. Set the insertion mode to "in body" and reprocess |
|
| 3389 | + /* Anything else */ |
|
| 3390 | + } else { |
|
| 3391 | + /* Parse error. Set the insertion mode to "in body" and reprocess |
|
| 3392 | 3392 | the token. */ |
| 3393 | - $this->mode = self::IN_BODY; |
|
| 3394 | - return $this->inBody($token); |
|
| 3395 | - } |
|
| 3396 | - } |
|
| 3393 | + $this->mode = self::IN_BODY; |
|
| 3394 | + return $this->inBody($token); |
|
| 3395 | + } |
|
| 3396 | + } |
|
| 3397 | 3397 | |
| 3398 | - private function inFrameset($token) { |
|
| 3399 | - /* Handle the token as follows: */ |
|
| 3398 | + private function inFrameset($token) { |
|
| 3399 | + /* Handle the token as follows: */ |
|
| 3400 | 3400 | |
| 3401 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3401 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3402 | 3402 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3403 | 3403 | U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ |
| 3404 | - if($token['type'] === HTML5::CHARACTR && |
|
| 3405 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3406 | - /* Append the character to the current node. */ |
|
| 3407 | - $this->insertText($token['data']); |
|
| 3408 | - |
|
| 3409 | - /* A comment token */ |
|
| 3410 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3411 | - /* Append a Comment node to the current node with the data |
|
| 3404 | + if($token['type'] === HTML5::CHARACTR && |
|
| 3405 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3406 | + /* Append the character to the current node. */ |
|
| 3407 | + $this->insertText($token['data']); |
|
| 3408 | + |
|
| 3409 | + /* A comment token */ |
|
| 3410 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3411 | + /* Append a Comment node to the current node with the data |
|
| 3412 | 3412 | attribute set to the data given in the comment token. */ |
| 3413 | - $this->insertComment($token['data']); |
|
| 3413 | + $this->insertComment($token['data']); |
|
| 3414 | 3414 | |
| 3415 | - /* A start tag with the tag name "frameset" */ |
|
| 3416 | - } elseif($token['name'] === 'frameset' && |
|
| 3417 | - $token['type'] === HTML5::STARTTAG) { |
|
| 3418 | - $this->insertElement($token); |
|
| 3415 | + /* A start tag with the tag name "frameset" */ |
|
| 3416 | + } elseif($token['name'] === 'frameset' && |
|
| 3417 | + $token['type'] === HTML5::STARTTAG) { |
|
| 3418 | + $this->insertElement($token); |
|
| 3419 | 3419 | |
| 3420 | - /* An end tag with the tag name "frameset" */ |
|
| 3421 | - } elseif($token['name'] === 'frameset' && |
|
| 3422 | - $token['type'] === HTML5::ENDTAG) { |
|
| 3423 | - /* If the current node is the root html element, then this is a |
|
| 3420 | + /* An end tag with the tag name "frameset" */ |
|
| 3421 | + } elseif($token['name'] === 'frameset' && |
|
| 3422 | + $token['type'] === HTML5::ENDTAG) { |
|
| 3423 | + /* If the current node is the root html element, then this is a |
|
| 3424 | 3424 | parse error; ignore the token. (innerHTML case) */ |
| 3425 | - if(end($this->stack)->nodeName === 'html') { |
|
| 3426 | - // Ignore |
|
| 3425 | + if(end($this->stack)->nodeName === 'html') { |
|
| 3426 | + // Ignore |
|
| 3427 | 3427 | |
| 3428 | - } else { |
|
| 3429 | - /* Otherwise, pop the current node from the stack of open |
|
| 3428 | + } else { |
|
| 3429 | + /* Otherwise, pop the current node from the stack of open |
|
| 3430 | 3430 | elements. */ |
| 3431 | - array_pop($this->stack); |
|
| 3431 | + array_pop($this->stack); |
|
| 3432 | 3432 | |
| 3433 | - /* If the parser was not originally created in order to handle |
|
| 3433 | + /* If the parser was not originally created in order to handle |
|
| 3434 | 3434 | the setting of an element's innerHTML attribute (innerHTML case), |
| 3435 | 3435 | and the current node is no longer a frameset element, then change |
| 3436 | 3436 | the insertion mode to "after frameset". */ |
| 3437 | - $this->mode = self::AFTR_FRAME; |
|
| 3438 | - } |
|
| 3439 | - |
|
| 3440 | - /* A start tag with the tag name "frame" */ |
|
| 3441 | - } elseif($token['name'] === 'frame' && |
|
| 3442 | - $token['type'] === HTML5::STARTTAG) { |
|
| 3443 | - /* Insert an HTML element for the token. */ |
|
| 3444 | - $this->insertElement($token); |
|
| 3445 | - |
|
| 3446 | - /* Immediately pop the current node off the stack of open elements. */ |
|
| 3447 | - array_pop($this->stack); |
|
| 3448 | - |
|
| 3449 | - /* A start tag with the tag name "noframes" */ |
|
| 3450 | - } elseif($token['name'] === 'noframes' && |
|
| 3451 | - $token['type'] === HTML5::STARTTAG) { |
|
| 3452 | - /* Process the token as if the insertion mode had been "in body". */ |
|
| 3453 | - $this->inBody($token); |
|
| 3454 | - |
|
| 3455 | - /* Anything else */ |
|
| 3456 | - } else { |
|
| 3457 | - /* Parse error. Ignore the token. */ |
|
| 3458 | - } |
|
| 3459 | - } |
|
| 3460 | - |
|
| 3461 | - private function afterFrameset($token) { |
|
| 3462 | - /* Handle the token as follows: */ |
|
| 3463 | - |
|
| 3464 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3437 | + $this->mode = self::AFTR_FRAME; |
|
| 3438 | + } |
|
| 3439 | + |
|
| 3440 | + /* A start tag with the tag name "frame" */ |
|
| 3441 | + } elseif($token['name'] === 'frame' && |
|
| 3442 | + $token['type'] === HTML5::STARTTAG) { |
|
| 3443 | + /* Insert an HTML element for the token. */ |
|
| 3444 | + $this->insertElement($token); |
|
| 3445 | + |
|
| 3446 | + /* Immediately pop the current node off the stack of open elements. */ |
|
| 3447 | + array_pop($this->stack); |
|
| 3448 | + |
|
| 3449 | + /* A start tag with the tag name "noframes" */ |
|
| 3450 | + } elseif($token['name'] === 'noframes' && |
|
| 3451 | + $token['type'] === HTML5::STARTTAG) { |
|
| 3452 | + /* Process the token as if the insertion mode had been "in body". */ |
|
| 3453 | + $this->inBody($token); |
|
| 3454 | + |
|
| 3455 | + /* Anything else */ |
|
| 3456 | + } else { |
|
| 3457 | + /* Parse error. Ignore the token. */ |
|
| 3458 | + } |
|
| 3459 | + } |
|
| 3460 | + |
|
| 3461 | + private function afterFrameset($token) { |
|
| 3462 | + /* Handle the token as follows: */ |
|
| 3463 | + |
|
| 3464 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3465 | 3465 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3466 | 3466 | U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ |
| 3467 | - if($token['type'] === HTML5::CHARACTR && |
|
| 3468 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3469 | - /* Append the character to the current node. */ |
|
| 3470 | - $this->insertText($token['data']); |
|
| 3471 | - |
|
| 3472 | - /* A comment token */ |
|
| 3473 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3474 | - /* Append a Comment node to the current node with the data |
|
| 3467 | + if($token['type'] === HTML5::CHARACTR && |
|
| 3468 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3469 | + /* Append the character to the current node. */ |
|
| 3470 | + $this->insertText($token['data']); |
|
| 3471 | + |
|
| 3472 | + /* A comment token */ |
|
| 3473 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3474 | + /* Append a Comment node to the current node with the data |
|
| 3475 | 3475 | attribute set to the data given in the comment token. */ |
| 3476 | - $this->insertComment($token['data']); |
|
| 3477 | - |
|
| 3478 | - /* An end tag with the tag name "html" */ |
|
| 3479 | - } elseif($token['name'] === 'html' && |
|
| 3480 | - $token['type'] === HTML5::ENDTAG) { |
|
| 3481 | - /* Switch to the trailing end phase. */ |
|
| 3482 | - $this->phase = self::END_PHASE; |
|
| 3483 | - |
|
| 3484 | - /* A start tag with the tag name "noframes" */ |
|
| 3485 | - } elseif($token['name'] === 'noframes' && |
|
| 3486 | - $token['type'] === HTML5::STARTTAG) { |
|
| 3487 | - /* Process the token as if the insertion mode had been "in body". */ |
|
| 3488 | - $this->inBody($token); |
|
| 3489 | - |
|
| 3490 | - /* Anything else */ |
|
| 3491 | - } else { |
|
| 3492 | - /* Parse error. Ignore the token. */ |
|
| 3493 | - } |
|
| 3494 | - } |
|
| 3495 | - |
|
| 3496 | - private function trailingEndPhase($token) { |
|
| 3497 | - /* After the main phase, as each token is emitted from the tokenisation |
|
| 3476 | + $this->insertComment($token['data']); |
|
| 3477 | + |
|
| 3478 | + /* An end tag with the tag name "html" */ |
|
| 3479 | + } elseif($token['name'] === 'html' && |
|
| 3480 | + $token['type'] === HTML5::ENDTAG) { |
|
| 3481 | + /* Switch to the trailing end phase. */ |
|
| 3482 | + $this->phase = self::END_PHASE; |
|
| 3483 | + |
|
| 3484 | + /* A start tag with the tag name "noframes" */ |
|
| 3485 | + } elseif($token['name'] === 'noframes' && |
|
| 3486 | + $token['type'] === HTML5::STARTTAG) { |
|
| 3487 | + /* Process the token as if the insertion mode had been "in body". */ |
|
| 3488 | + $this->inBody($token); |
|
| 3489 | + |
|
| 3490 | + /* Anything else */ |
|
| 3491 | + } else { |
|
| 3492 | + /* Parse error. Ignore the token. */ |
|
| 3493 | + } |
|
| 3494 | + } |
|
| 3495 | + |
|
| 3496 | + private function trailingEndPhase($token) { |
|
| 3497 | + /* After the main phase, as each token is emitted from the tokenisation |
|
| 3498 | 3498 | stage, it must be processed as described in this section. */ |
| 3499 | 3499 | |
| 3500 | - /* A DOCTYPE token */ |
|
| 3501 | - if($token['type'] === HTML5::DOCTYPE) { |
|
| 3502 | - // Parse error. Ignore the token. |
|
| 3500 | + /* A DOCTYPE token */ |
|
| 3501 | + if($token['type'] === HTML5::DOCTYPE) { |
|
| 3502 | + // Parse error. Ignore the token. |
|
| 3503 | 3503 | |
| 3504 | - /* A comment token */ |
|
| 3505 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3506 | - /* Append a Comment node to the Document object with the data |
|
| 3504 | + /* A comment token */ |
|
| 3505 | + } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3506 | + /* Append a Comment node to the Document object with the data |
|
| 3507 | 3507 | attribute set to the data given in the comment token. */ |
| 3508 | - $comment = $this->dom->createComment($token['data']); |
|
| 3509 | - $this->dom->appendChild($comment); |
|
| 3508 | + $comment = $this->dom->createComment($token['data']); |
|
| 3509 | + $this->dom->appendChild($comment); |
|
| 3510 | 3510 | |
| 3511 | - /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3511 | + /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
|
| 3512 | 3512 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3513 | 3513 | or U+0020 SPACE */ |
| 3514 | - } elseif($token['type'] === HTML5::CHARACTR && |
|
| 3515 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3516 | - /* Process the token as it would be processed in the main phase. */ |
|
| 3517 | - $this->mainPhase($token); |
|
| 3514 | + } elseif($token['type'] === HTML5::CHARACTR && |
|
| 3515 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
|
| 3516 | + /* Process the token as it would be processed in the main phase. */ |
|
| 3517 | + $this->mainPhase($token); |
|
| 3518 | 3518 | |
| 3519 | - /* A character token that is not one of U+0009 CHARACTER TABULATION, |
|
| 3519 | + /* A character token that is not one of U+0009 CHARACTER TABULATION, |
|
| 3520 | 3520 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3521 | 3521 | or U+0020 SPACE. Or a start tag token. Or an end tag token. */ |
| 3522 | - } elseif(($token['type'] === HTML5::CHARACTR && |
|
| 3523 | - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || |
|
| 3524 | - $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) { |
|
| 3525 | - /* Parse error. Switch back to the main phase and reprocess the |
|
| 3522 | + } elseif(($token['type'] === HTML5::CHARACTR && |
|
| 3523 | + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || |
|
| 3524 | + $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) { |
|
| 3525 | + /* Parse error. Switch back to the main phase and reprocess the |
|
| 3526 | 3526 | token. */ |
| 3527 | - $this->phase = self::MAIN_PHASE; |
|
| 3528 | - return $this->mainPhase($token); |
|
| 3529 | - |
|
| 3530 | - /* An end-of-file token */ |
|
| 3531 | - } elseif($token['type'] === HTML5::EOF) { |
|
| 3532 | - /* OMG DONE!! */ |
|
| 3533 | - } |
|
| 3534 | - } |
|
| 3535 | - |
|
| 3536 | - private function insertElement($token, $append = true, $check = false) { |
|
| 3537 | - // Proprietary workaround for libxml2's limitations with tag names |
|
| 3538 | - if ($check) { |
|
| 3539 | - // Slightly modified HTML5 tag-name modification, |
|
| 3540 | - // removing anything that's not an ASCII letter, digit, or hyphen |
|
| 3541 | - $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']); |
|
| 3542 | - // Remove leading hyphens and numbers |
|
| 3543 | - $token['name'] = ltrim($token['name'], '-0..9'); |
|
| 3544 | - // In theory, this should ever be needed, but just in case |
|
| 3545 | - if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice |
|
| 3546 | - } |
|
| 3527 | + $this->phase = self::MAIN_PHASE; |
|
| 3528 | + return $this->mainPhase($token); |
|
| 3529 | + |
|
| 3530 | + /* An end-of-file token */ |
|
| 3531 | + } elseif($token['type'] === HTML5::EOF) { |
|
| 3532 | + /* OMG DONE!! */ |
|
| 3533 | + } |
|
| 3534 | + } |
|
| 3535 | + |
|
| 3536 | + private function insertElement($token, $append = true, $check = false) { |
|
| 3537 | + // Proprietary workaround for libxml2's limitations with tag names |
|
| 3538 | + if ($check) { |
|
| 3539 | + // Slightly modified HTML5 tag-name modification, |
|
| 3540 | + // removing anything that's not an ASCII letter, digit, or hyphen |
|
| 3541 | + $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']); |
|
| 3542 | + // Remove leading hyphens and numbers |
|
| 3543 | + $token['name'] = ltrim($token['name'], '-0..9'); |
|
| 3544 | + // In theory, this should ever be needed, but just in case |
|
| 3545 | + if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice |
|
| 3546 | + } |
|
| 3547 | 3547 | |
| 3548 | - $el = $this->dom->createElement($token['name']); |
|
| 3548 | + $el = $this->dom->createElement($token['name']); |
|
| 3549 | 3549 | |
| 3550 | - foreach($token['attr'] as $attr) { |
|
| 3551 | - if(!$el->hasAttribute($attr['name'])) { |
|
| 3552 | - $el->setAttribute($attr['name'], $attr['value']); |
|
| 3553 | - } |
|
| 3554 | - } |
|
| 3550 | + foreach($token['attr'] as $attr) { |
|
| 3551 | + if(!$el->hasAttribute($attr['name'])) { |
|
| 3552 | + $el->setAttribute($attr['name'], $attr['value']); |
|
| 3553 | + } |
|
| 3554 | + } |
|
| 3555 | 3555 | |
| 3556 | - $this->appendToRealParent($el); |
|
| 3557 | - $this->stack[] = $el; |
|
| 3556 | + $this->appendToRealParent($el); |
|
| 3557 | + $this->stack[] = $el; |
|
| 3558 | 3558 | |
| 3559 | - return $el; |
|
| 3560 | - } |
|
| 3559 | + return $el; |
|
| 3560 | + } |
|
| 3561 | 3561 | |
| 3562 | - private function insertText($data) { |
|
| 3563 | - $text = $this->dom->createTextNode($data); |
|
| 3564 | - $this->appendToRealParent($text); |
|
| 3565 | - } |
|
| 3562 | + private function insertText($data) { |
|
| 3563 | + $text = $this->dom->createTextNode($data); |
|
| 3564 | + $this->appendToRealParent($text); |
|
| 3565 | + } |
|
| 3566 | 3566 | |
| 3567 | - private function insertComment($data) { |
|
| 3568 | - $comment = $this->dom->createComment($data); |
|
| 3569 | - $this->appendToRealParent($comment); |
|
| 3570 | - } |
|
| 3567 | + private function insertComment($data) { |
|
| 3568 | + $comment = $this->dom->createComment($data); |
|
| 3569 | + $this->appendToRealParent($comment); |
|
| 3570 | + } |
|
| 3571 | 3571 | |
| 3572 | - private function appendToRealParent($node) { |
|
| 3573 | - if($this->foster_parent === null) { |
|
| 3574 | - end($this->stack)->appendChild($node); |
|
| 3572 | + private function appendToRealParent($node) { |
|
| 3573 | + if($this->foster_parent === null) { |
|
| 3574 | + end($this->stack)->appendChild($node); |
|
| 3575 | 3575 | |
| 3576 | - } elseif($this->foster_parent !== null) { |
|
| 3577 | - /* If the foster parent element is the parent element of the |
|
| 3576 | + } elseif($this->foster_parent !== null) { |
|
| 3577 | + /* If the foster parent element is the parent element of the |
|
| 3578 | 3578 | last table element in the stack of open elements, then the new |
| 3579 | 3579 | node must be inserted immediately before the last table element |
| 3580 | 3580 | in the stack of open elements in the foster parent element; |
| 3581 | 3581 | otherwise, the new node must be appended to the foster parent |
| 3582 | 3582 | element. */ |
| 3583 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 3584 | - if($this->stack[$n]->nodeName === 'table' && |
|
| 3585 | - $this->stack[$n]->parentNode !== null) { |
|
| 3586 | - $table = $this->stack[$n]; |
|
| 3587 | - break; |
|
| 3588 | - } |
|
| 3589 | - } |
|
| 3590 | - |
|
| 3591 | - if(isset($table) && $this->foster_parent->isSameNode($table->parentNode)) |
|
| 3592 | - $this->foster_parent->insertBefore($node, $table); |
|
| 3593 | - else |
|
| 3594 | - $this->foster_parent->appendChild($node); |
|
| 3595 | - |
|
| 3596 | - $this->foster_parent = null; |
|
| 3597 | - } |
|
| 3598 | - } |
|
| 3599 | - |
|
| 3600 | - private function elementInScope($el, $table = false) { |
|
| 3601 | - if(is_array($el)) { |
|
| 3602 | - foreach($el as $element) { |
|
| 3603 | - if($this->elementInScope($element, $table)) { |
|
| 3604 | - return true; |
|
| 3605 | - } |
|
| 3606 | - } |
|
| 3607 | - |
|
| 3608 | - return false; |
|
| 3609 | - } |
|
| 3610 | - |
|
| 3611 | - $leng = count($this->stack); |
|
| 3612 | - |
|
| 3613 | - for($n = 0; $n < $leng; $n++) { |
|
| 3614 | - /* 1. Initialise node to be the current node (the bottommost node of |
|
| 3583 | + for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 3584 | + if($this->stack[$n]->nodeName === 'table' && |
|
| 3585 | + $this->stack[$n]->parentNode !== null) { |
|
| 3586 | + $table = $this->stack[$n]; |
|
| 3587 | + break; |
|
| 3588 | + } |
|
| 3589 | + } |
|
| 3590 | + |
|
| 3591 | + if(isset($table) && $this->foster_parent->isSameNode($table->parentNode)) |
|
| 3592 | + $this->foster_parent->insertBefore($node, $table); |
|
| 3593 | + else |
|
| 3594 | + $this->foster_parent->appendChild($node); |
|
| 3595 | + |
|
| 3596 | + $this->foster_parent = null; |
|
| 3597 | + } |
|
| 3598 | + } |
|
| 3599 | + |
|
| 3600 | + private function elementInScope($el, $table = false) { |
|
| 3601 | + if(is_array($el)) { |
|
| 3602 | + foreach($el as $element) { |
|
| 3603 | + if($this->elementInScope($element, $table)) { |
|
| 3604 | + return true; |
|
| 3605 | + } |
|
| 3606 | + } |
|
| 3607 | + |
|
| 3608 | + return false; |
|
| 3609 | + } |
|
| 3610 | + |
|
| 3611 | + $leng = count($this->stack); |
|
| 3612 | + |
|
| 3613 | + for($n = 0; $n < $leng; $n++) { |
|
| 3614 | + /* 1. Initialise node to be the current node (the bottommost node of |
|
| 3615 | 3615 | the stack). */ |
| 3616 | - $node = $this->stack[$leng - 1 - $n]; |
|
| 3616 | + $node = $this->stack[$leng - 1 - $n]; |
|
| 3617 | 3617 | |
| 3618 | - if($node->tagName === $el) { |
|
| 3619 | - /* 2. If node is the target node, terminate in a match state. */ |
|
| 3620 | - return true; |
|
| 3618 | + if($node->tagName === $el) { |
|
| 3619 | + /* 2. If node is the target node, terminate in a match state. */ |
|
| 3620 | + return true; |
|
| 3621 | 3621 | |
| 3622 | - } elseif($node->tagName === 'table') { |
|
| 3623 | - /* 3. Otherwise, if node is a table element, terminate in a failure |
|
| 3622 | + } elseif($node->tagName === 'table') { |
|
| 3623 | + /* 3. Otherwise, if node is a table element, terminate in a failure |
|
| 3624 | 3624 | state. */ |
| 3625 | - return false; |
|
| 3625 | + return false; |
|
| 3626 | 3626 | |
| 3627 | - } elseif($table === true && in_array($node->tagName, array('caption', 'td', |
|
| 3628 | - 'th', 'button', 'marquee', 'object'))) { |
|
| 3629 | - /* 4. Otherwise, if the algorithm is the "has an element in scope" |
|
| 3627 | + } elseif($table === true && in_array($node->tagName, array('caption', 'td', |
|
| 3628 | + 'th', 'button', 'marquee', 'object'))) { |
|
| 3629 | + /* 4. Otherwise, if the algorithm is the "has an element in scope" |
|
| 3630 | 3630 | variant (rather than the "has an element in table scope" variant), |
| 3631 | 3631 | and node is one of the following, terminate in a failure state. */ |
| 3632 | - return false; |
|
| 3632 | + return false; |
|
| 3633 | 3633 | |
| 3634 | - } elseif($node === $node->ownerDocument->documentElement) { |
|
| 3635 | - /* 5. Otherwise, if node is an html element (root element), terminate |
|
| 3634 | + } elseif($node === $node->ownerDocument->documentElement) { |
|
| 3635 | + /* 5. Otherwise, if node is an html element (root element), terminate |
|
| 3636 | 3636 | in a failure state. (This can only happen if the node is the topmost |
| 3637 | 3637 | node of the stack of open elements, and prevents the next step from |
| 3638 | 3638 | being invoked if there are no more elements in the stack.) */ |
| 3639 | - return false; |
|
| 3640 | - } |
|
| 3639 | + return false; |
|
| 3640 | + } |
|
| 3641 | 3641 | |
| 3642 | - /* Otherwise, set node to the previous entry in the stack of open |
|
| 3642 | + /* Otherwise, set node to the previous entry in the stack of open |
|
| 3643 | 3643 | elements and return to step 2. (This will never fail, since the loop |
| 3644 | 3644 | will always terminate in the previous step if the top of the stack |
| 3645 | 3645 | is reached.) */ |
| 3646 | - } |
|
| 3647 | - } |
|
| 3646 | + } |
|
| 3647 | + } |
|
| 3648 | 3648 | |
| 3649 | - private function reconstructActiveFormattingElements() { |
|
| 3650 | - /* 1. If there are no entries in the list of active formatting elements, |
|
| 3649 | + private function reconstructActiveFormattingElements() { |
|
| 3650 | + /* 1. If there are no entries in the list of active formatting elements, |
|
| 3651 | 3651 | then there is nothing to reconstruct; stop this algorithm. */ |
| 3652 | - $formatting_elements = count($this->a_formatting); |
|
| 3652 | + $formatting_elements = count($this->a_formatting); |
|
| 3653 | 3653 | |
| 3654 | - if($formatting_elements === 0) { |
|
| 3655 | - return false; |
|
| 3656 | - } |
|
| 3654 | + if($formatting_elements === 0) { |
|
| 3655 | + return false; |
|
| 3656 | + } |
|
| 3657 | 3657 | |
| 3658 | - /* 3. Let entry be the last (most recently added) element in the list |
|
| 3658 | + /* 3. Let entry be the last (most recently added) element in the list |
|
| 3659 | 3659 | of active formatting elements. */ |
| 3660 | - $entry = end($this->a_formatting); |
|
| 3660 | + $entry = end($this->a_formatting); |
|
| 3661 | 3661 | |
| 3662 | - /* 2. If the last (most recently added) entry in the list of active |
|
| 3662 | + /* 2. If the last (most recently added) entry in the list of active |
|
| 3663 | 3663 | formatting elements is a marker, or if it is an element that is in the |
| 3664 | 3664 | stack of open elements, then there is nothing to reconstruct; stop this |
| 3665 | 3665 | algorithm. */ |
| 3666 | - if($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3667 | - return false; |
|
| 3668 | - } |
|
| 3666 | + if($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3667 | + return false; |
|
| 3668 | + } |
|
| 3669 | 3669 | |
| 3670 | - for($a = $formatting_elements - 1; $a >= 0; true) { |
|
| 3671 | - /* 4. If there are no entries before entry in the list of active |
|
| 3670 | + for($a = $formatting_elements - 1; $a >= 0; true) { |
|
| 3671 | + /* 4. If there are no entries before entry in the list of active |
|
| 3672 | 3672 | formatting elements, then jump to step 8. */ |
| 3673 | - if($a === 0) { |
|
| 3674 | - $step_seven = false; |
|
| 3675 | - break; |
|
| 3676 | - } |
|
| 3673 | + if($a === 0) { |
|
| 3674 | + $step_seven = false; |
|
| 3675 | + break; |
|
| 3676 | + } |
|
| 3677 | 3677 | |
| 3678 | - /* 5. Let entry be the entry one earlier than entry in the list of |
|
| 3678 | + /* 5. Let entry be the entry one earlier than entry in the list of |
|
| 3679 | 3679 | active formatting elements. */ |
| 3680 | - $a--; |
|
| 3681 | - $entry = $this->a_formatting[$a]; |
|
| 3680 | + $a--; |
|
| 3681 | + $entry = $this->a_formatting[$a]; |
|
| 3682 | 3682 | |
| 3683 | - /* 6. If entry is neither a marker nor an element that is also in |
|
| 3683 | + /* 6. If entry is neither a marker nor an element that is also in |
|
| 3684 | 3684 | thetack of open elements, go to step 4. */ |
| 3685 | - if($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3686 | - break; |
|
| 3687 | - } |
|
| 3688 | - } |
|
| 3685 | + if($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3686 | + break; |
|
| 3687 | + } |
|
| 3688 | + } |
|
| 3689 | 3689 | |
| 3690 | - while(true) { |
|
| 3691 | - /* 7. Let entry be the element one later than entry in the list of |
|
| 3690 | + while(true) { |
|
| 3691 | + /* 7. Let entry be the element one later than entry in the list of |
|
| 3692 | 3692 | active formatting elements. */ |
| 3693 | - if(isset($step_seven) && $step_seven === true) { |
|
| 3694 | - $a++; |
|
| 3695 | - $entry = $this->a_formatting[$a]; |
|
| 3696 | - } |
|
| 3693 | + if(isset($step_seven) && $step_seven === true) { |
|
| 3694 | + $a++; |
|
| 3695 | + $entry = $this->a_formatting[$a]; |
|
| 3696 | + } |
|
| 3697 | 3697 | |
| 3698 | - /* 8. Perform a shallow clone of the element entry to obtain clone. */ |
|
| 3699 | - $clone = $entry->cloneNode(); |
|
| 3698 | + /* 8. Perform a shallow clone of the element entry to obtain clone. */ |
|
| 3699 | + $clone = $entry->cloneNode(); |
|
| 3700 | 3700 | |
| 3701 | - /* 9. Append clone to the current node and push it onto the stack |
|
| 3701 | + /* 9. Append clone to the current node and push it onto the stack |
|
| 3702 | 3702 | of open elements so that it is the new current node. */ |
| 3703 | - end($this->stack)->appendChild($clone); |
|
| 3704 | - $this->stack[] = $clone; |
|
| 3703 | + end($this->stack)->appendChild($clone); |
|
| 3704 | + $this->stack[] = $clone; |
|
| 3705 | 3705 | |
| 3706 | - /* 10. Replace the entry for entry in the list with an entry for |
|
| 3706 | + /* 10. Replace the entry for entry in the list with an entry for |
|
| 3707 | 3707 | clone. */ |
| 3708 | - $this->a_formatting[$a] = $clone; |
|
| 3708 | + $this->a_formatting[$a] = $clone; |
|
| 3709 | 3709 | |
| 3710 | - /* 11. If the entry for clone in the list of active formatting |
|
| 3710 | + /* 11. If the entry for clone in the list of active formatting |
|
| 3711 | 3711 | elements is not the last entry in the list, return to step 7. */ |
| 3712 | - if(end($this->a_formatting) !== $clone) { |
|
| 3713 | - $step_seven = true; |
|
| 3714 | - } else { |
|
| 3715 | - break; |
|
| 3716 | - } |
|
| 3717 | - } |
|
| 3718 | - } |
|
| 3719 | - |
|
| 3720 | - private function clearTheActiveFormattingElementsUpToTheLastMarker() { |
|
| 3721 | - /* When the steps below require the UA to clear the list of active |
|
| 3712 | + if(end($this->a_formatting) !== $clone) { |
|
| 3713 | + $step_seven = true; |
|
| 3714 | + } else { |
|
| 3715 | + break; |
|
| 3716 | + } |
|
| 3717 | + } |
|
| 3718 | + } |
|
| 3719 | + |
|
| 3720 | + private function clearTheActiveFormattingElementsUpToTheLastMarker() { |
|
| 3721 | + /* When the steps below require the UA to clear the list of active |
|
| 3722 | 3722 | formatting elements up to the last marker, the UA must perform the |
| 3723 | 3723 | following steps: */ |
| 3724 | 3724 | |
| 3725 | - while(true) { |
|
| 3726 | - /* 1. Let entry be the last (most recently added) entry in the list |
|
| 3725 | + while(true) { |
|
| 3726 | + /* 1. Let entry be the last (most recently added) entry in the list |
|
| 3727 | 3727 | of active formatting elements. */ |
| 3728 | - $entry = end($this->a_formatting); |
|
| 3728 | + $entry = end($this->a_formatting); |
|
| 3729 | 3729 | |
| 3730 | - /* 2. Remove entry from the list of active formatting elements. */ |
|
| 3731 | - array_pop($this->a_formatting); |
|
| 3730 | + /* 2. Remove entry from the list of active formatting elements. */ |
|
| 3731 | + array_pop($this->a_formatting); |
|
| 3732 | 3732 | |
| 3733 | - /* 3. If entry was a marker, then stop the algorithm at this point. |
|
| 3733 | + /* 3. If entry was a marker, then stop the algorithm at this point. |
|
| 3734 | 3734 | The list has been cleared up to the last marker. */ |
| 3735 | - if($entry === self::MARKER) { |
|
| 3736 | - break; |
|
| 3737 | - } |
|
| 3738 | - } |
|
| 3739 | - } |
|
| 3740 | - |
|
| 3741 | - private function generateImpliedEndTags($exclude = array()) { |
|
| 3742 | - /* When the steps below require the UA to generate implied end tags, |
|
| 3735 | + if($entry === self::MARKER) { |
|
| 3736 | + break; |
|
| 3737 | + } |
|
| 3738 | + } |
|
| 3739 | + } |
|
| 3740 | + |
|
| 3741 | + private function generateImpliedEndTags($exclude = array()) { |
|
| 3742 | + /* When the steps below require the UA to generate implied end tags, |
|
| 3743 | 3743 | then, if the current node is a dd element, a dt element, an li element, |
| 3744 | 3744 | a p element, a td element, a th element, or a tr element, the UA must |
| 3745 | 3745 | act as if an end tag with the respective tag name had been seen and |
| 3746 | 3746 | then generate implied end tags again. */ |
| 3747 | - $node = end($this->stack); |
|
| 3748 | - $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude); |
|
| 3747 | + $node = end($this->stack); |
|
| 3748 | + $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude); |
|
| 3749 | 3749 | |
| 3750 | - while(in_array(end($this->stack)->nodeName, $elements)) { |
|
| 3751 | - array_pop($this->stack); |
|
| 3752 | - } |
|
| 3753 | - } |
|
| 3750 | + while(in_array(end($this->stack)->nodeName, $elements)) { |
|
| 3751 | + array_pop($this->stack); |
|
| 3752 | + } |
|
| 3753 | + } |
|
| 3754 | 3754 | |
| 3755 | - private function getElementCategory($node) { |
|
| 3756 | - $name = $node->tagName; |
|
| 3757 | - if(in_array($name, $this->special)) |
|
| 3758 | - return self::SPECIAL; |
|
| 3755 | + private function getElementCategory($node) { |
|
| 3756 | + $name = $node->tagName; |
|
| 3757 | + if(in_array($name, $this->special)) |
|
| 3758 | + return self::SPECIAL; |
|
| 3759 | 3759 | |
| 3760 | - elseif(in_array($name, $this->scoping)) |
|
| 3761 | - return self::SCOPING; |
|
| 3760 | + elseif(in_array($name, $this->scoping)) |
|
| 3761 | + return self::SCOPING; |
|
| 3762 | 3762 | |
| 3763 | - elseif(in_array($name, $this->formatting)) |
|
| 3764 | - return self::FORMATTING; |
|
| 3763 | + elseif(in_array($name, $this->formatting)) |
|
| 3764 | + return self::FORMATTING; |
|
| 3765 | 3765 | |
| 3766 | - else |
|
| 3767 | - return self::PHRASING; |
|
| 3768 | - } |
|
| 3766 | + else |
|
| 3767 | + return self::PHRASING; |
|
| 3768 | + } |
|
| 3769 | 3769 | |
| 3770 | - private function clearStackToTableContext($elements) { |
|
| 3771 | - /* When the steps above require the UA to clear the stack back to a |
|
| 3770 | + private function clearStackToTableContext($elements) { |
|
| 3771 | + /* When the steps above require the UA to clear the stack back to a |
|
| 3772 | 3772 | table context, it means that the UA must, while the current node is not |
| 3773 | 3773 | a table element or an html element, pop elements from the stack of open |
| 3774 | 3774 | elements. If this causes any elements to be popped from the stack, then |
| 3775 | 3775 | this is a parse error. */ |
| 3776 | - while(true) { |
|
| 3777 | - $node = end($this->stack)->nodeName; |
|
| 3778 | - |
|
| 3779 | - if(in_array($node, $elements)) { |
|
| 3780 | - break; |
|
| 3781 | - } else { |
|
| 3782 | - array_pop($this->stack); |
|
| 3783 | - } |
|
| 3784 | - } |
|
| 3785 | - } |
|
| 3786 | - |
|
| 3787 | - private function resetInsertionMode() { |
|
| 3788 | - /* 1. Let last be false. */ |
|
| 3789 | - $last = false; |
|
| 3790 | - $leng = count($this->stack); |
|
| 3791 | - |
|
| 3792 | - for($n = $leng - 1; $n >= 0; $n--) { |
|
| 3793 | - /* 2. Let node be the last node in the stack of open elements. */ |
|
| 3794 | - $node = $this->stack[$n]; |
|
| 3795 | - |
|
| 3796 | - /* 3. If node is the first node in the stack of open elements, then |
|
| 3776 | + while(true) { |
|
| 3777 | + $node = end($this->stack)->nodeName; |
|
| 3778 | + |
|
| 3779 | + if(in_array($node, $elements)) { |
|
| 3780 | + break; |
|
| 3781 | + } else { |
|
| 3782 | + array_pop($this->stack); |
|
| 3783 | + } |
|
| 3784 | + } |
|
| 3785 | + } |
|
| 3786 | + |
|
| 3787 | + private function resetInsertionMode() { |
|
| 3788 | + /* 1. Let last be false. */ |
|
| 3789 | + $last = false; |
|
| 3790 | + $leng = count($this->stack); |
|
| 3791 | + |
|
| 3792 | + for($n = $leng - 1; $n >= 0; $n--) { |
|
| 3793 | + /* 2. Let node be the last node in the stack of open elements. */ |
|
| 3794 | + $node = $this->stack[$n]; |
|
| 3795 | + |
|
| 3796 | + /* 3. If node is the first node in the stack of open elements, then |
|
| 3797 | 3797 | set last to true. If the element whose innerHTML attribute is being |
| 3798 | 3798 | set is neither a td element nor a th element, then set node to the |
| 3799 | 3799 | element whose innerHTML attribute is being set. (innerHTML case) */ |
| 3800 | - if($this->stack[0]->isSameNode($node)) { |
|
| 3801 | - $last = true; |
|
| 3802 | - } |
|
| 3800 | + if($this->stack[0]->isSameNode($node)) { |
|
| 3801 | + $last = true; |
|
| 3802 | + } |
|
| 3803 | 3803 | |
| 3804 | - /* 4. If node is a select element, then switch the insertion mode to |
|
| 3804 | + /* 4. If node is a select element, then switch the insertion mode to |
|
| 3805 | 3805 | "in select" and abort these steps. (innerHTML case) */ |
| 3806 | - if($node->nodeName === 'select') { |
|
| 3807 | - $this->mode = self::IN_SELECT; |
|
| 3808 | - break; |
|
| 3806 | + if($node->nodeName === 'select') { |
|
| 3807 | + $this->mode = self::IN_SELECT; |
|
| 3808 | + break; |
|
| 3809 | 3809 | |
| 3810 | - /* 5. If node is a td or th element, then switch the insertion mode |
|
| 3810 | + /* 5. If node is a td or th element, then switch the insertion mode |
|
| 3811 | 3811 | to "in cell" and abort these steps. */ |
| 3812 | - } elseif($node->nodeName === 'td' || $node->nodeName === 'th') { |
|
| 3813 | - $this->mode = self::IN_CELL; |
|
| 3814 | - break; |
|
| 3812 | + } elseif($node->nodeName === 'td' || $node->nodeName === 'th') { |
|
| 3813 | + $this->mode = self::IN_CELL; |
|
| 3814 | + break; |
|
| 3815 | 3815 | |
| 3816 | - /* 6. If node is a tr element, then switch the insertion mode to |
|
| 3816 | + /* 6. If node is a tr element, then switch the insertion mode to |
|
| 3817 | 3817 | "in row" and abort these steps. */ |
| 3818 | - } elseif($node->nodeName === 'tr') { |
|
| 3819 | - $this->mode = self::IN_ROW; |
|
| 3820 | - break; |
|
| 3818 | + } elseif($node->nodeName === 'tr') { |
|
| 3819 | + $this->mode = self::IN_ROW; |
|
| 3820 | + break; |
|
| 3821 | 3821 | |
| 3822 | - /* 7. If node is a tbody, thead, or tfoot element, then switch the |
|
| 3822 | + /* 7. If node is a tbody, thead, or tfoot element, then switch the |
|
| 3823 | 3823 | insertion mode to "in table body" and abort these steps. */ |
| 3824 | - } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) { |
|
| 3825 | - $this->mode = self::IN_TBODY; |
|
| 3826 | - break; |
|
| 3824 | + } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) { |
|
| 3825 | + $this->mode = self::IN_TBODY; |
|
| 3826 | + break; |
|
| 3827 | 3827 | |
| 3828 | - /* 8. If node is a caption element, then switch the insertion mode |
|
| 3828 | + /* 8. If node is a caption element, then switch the insertion mode |
|
| 3829 | 3829 | to "in caption" and abort these steps. */ |
| 3830 | - } elseif($node->nodeName === 'caption') { |
|
| 3831 | - $this->mode = self::IN_CAPTION; |
|
| 3832 | - break; |
|
| 3830 | + } elseif($node->nodeName === 'caption') { |
|
| 3831 | + $this->mode = self::IN_CAPTION; |
|
| 3832 | + break; |
|
| 3833 | 3833 | |
| 3834 | - /* 9. If node is a colgroup element, then switch the insertion mode |
|
| 3834 | + /* 9. If node is a colgroup element, then switch the insertion mode |
|
| 3835 | 3835 | to "in column group" and abort these steps. (innerHTML case) */ |
| 3836 | - } elseif($node->nodeName === 'colgroup') { |
|
| 3837 | - $this->mode = self::IN_CGROUP; |
|
| 3838 | - break; |
|
| 3836 | + } elseif($node->nodeName === 'colgroup') { |
|
| 3837 | + $this->mode = self::IN_CGROUP; |
|
| 3838 | + break; |
|
| 3839 | 3839 | |
| 3840 | - /* 10. If node is a table element, then switch the insertion mode |
|
| 3840 | + /* 10. If node is a table element, then switch the insertion mode |
|
| 3841 | 3841 | to "in table" and abort these steps. */ |
| 3842 | - } elseif($node->nodeName === 'table') { |
|
| 3843 | - $this->mode = self::IN_TABLE; |
|
| 3844 | - break; |
|
| 3842 | + } elseif($node->nodeName === 'table') { |
|
| 3843 | + $this->mode = self::IN_TABLE; |
|
| 3844 | + break; |
|
| 3845 | 3845 | |
| 3846 | - /* 11. If node is a head element, then switch the insertion mode |
|
| 3846 | + /* 11. If node is a head element, then switch the insertion mode |
|
| 3847 | 3847 | to "in body" ("in body"! not "in head"!) and abort these steps. |
| 3848 | 3848 | (innerHTML case) */ |
| 3849 | - } elseif($node->nodeName === 'head') { |
|
| 3850 | - $this->mode = self::IN_BODY; |
|
| 3851 | - break; |
|
| 3849 | + } elseif($node->nodeName === 'head') { |
|
| 3850 | + $this->mode = self::IN_BODY; |
|
| 3851 | + break; |
|
| 3852 | 3852 | |
| 3853 | - /* 12. If node is a body element, then switch the insertion mode to |
|
| 3853 | + /* 12. If node is a body element, then switch the insertion mode to |
|
| 3854 | 3854 | "in body" and abort these steps. */ |
| 3855 | - } elseif($node->nodeName === 'body') { |
|
| 3856 | - $this->mode = self::IN_BODY; |
|
| 3857 | - break; |
|
| 3855 | + } elseif($node->nodeName === 'body') { |
|
| 3856 | + $this->mode = self::IN_BODY; |
|
| 3857 | + break; |
|
| 3858 | 3858 | |
| 3859 | - /* 13. If node is a frameset element, then switch the insertion |
|
| 3859 | + /* 13. If node is a frameset element, then switch the insertion |
|
| 3860 | 3860 | mode to "in frameset" and abort these steps. (innerHTML case) */ |
| 3861 | - } elseif($node->nodeName === 'frameset') { |
|
| 3862 | - $this->mode = self::IN_FRAME; |
|
| 3863 | - break; |
|
| 3861 | + } elseif($node->nodeName === 'frameset') { |
|
| 3862 | + $this->mode = self::IN_FRAME; |
|
| 3863 | + break; |
|
| 3864 | 3864 | |
| 3865 | - /* 14. If node is an html element, then: if the head element |
|
| 3865 | + /* 14. If node is an html element, then: if the head element |
|
| 3866 | 3866 | pointer is null, switch the insertion mode to "before head", |
| 3867 | 3867 | otherwise, switch the insertion mode to "after head". In either |
| 3868 | 3868 | case, abort these steps. (innerHTML case) */ |
| 3869 | - } elseif($node->nodeName === 'html') { |
|
| 3870 | - $this->mode = ($this->head_pointer === null) |
|
| 3871 | - ? self::BEFOR_HEAD |
|
| 3872 | - : self::AFTER_HEAD; |
|
| 3869 | + } elseif($node->nodeName === 'html') { |
|
| 3870 | + $this->mode = ($this->head_pointer === null) |
|
| 3871 | + ? self::BEFOR_HEAD |
|
| 3872 | + : self::AFTER_HEAD; |
|
| 3873 | 3873 | |
| 3874 | - break; |
|
| 3874 | + break; |
|
| 3875 | 3875 | |
| 3876 | - /* 15. If last is true, then set the insertion mode to "in body" |
|
| 3876 | + /* 15. If last is true, then set the insertion mode to "in body" |
|
| 3877 | 3877 | and abort these steps. (innerHTML case) */ |
| 3878 | - } elseif($last) { |
|
| 3879 | - $this->mode = self::IN_BODY; |
|
| 3880 | - break; |
|
| 3881 | - } |
|
| 3882 | - } |
|
| 3883 | - } |
|
| 3884 | - |
|
| 3885 | - private function closeCell() { |
|
| 3886 | - /* If the stack of open elements has a td or th element in table scope, |
|
| 3878 | + } elseif($last) { |
|
| 3879 | + $this->mode = self::IN_BODY; |
|
| 3880 | + break; |
|
| 3881 | + } |
|
| 3882 | + } |
|
| 3883 | + } |
|
| 3884 | + |
|
| 3885 | + private function closeCell() { |
|
| 3886 | + /* If the stack of open elements has a td or th element in table scope, |
|
| 3887 | 3887 | then act as if an end tag token with that tag name had been seen. */ |
| 3888 | - foreach(array('td', 'th') as $cell) { |
|
| 3889 | - if($this->elementInScope($cell, true)) { |
|
| 3890 | - $this->inCell(array( |
|
| 3891 | - 'name' => $cell, |
|
| 3892 | - 'type' => HTML5::ENDTAG |
|
| 3893 | - )); |
|
| 3894 | - |
|
| 3895 | - break; |
|
| 3896 | - } |
|
| 3897 | - } |
|
| 3898 | - } |
|
| 3899 | - |
|
| 3900 | - public function save() { |
|
| 3901 | - return $this->dom; |
|
| 3902 | - } |
|
| 3888 | + foreach(array('td', 'th') as $cell) { |
|
| 3889 | + if($this->elementInScope($cell, true)) { |
|
| 3890 | + $this->inCell(array( |
|
| 3891 | + 'name' => $cell, |
|
| 3892 | + 'type' => HTML5::ENDTAG |
|
| 3893 | + )); |
|
| 3894 | + |
|
| 3895 | + break; |
|
| 3896 | + } |
|
| 3897 | + } |
|
| 3898 | + } |
|
| 3899 | + |
|
| 3900 | + public function save() { |
|
| 3901 | + return $this->dom; |
|
| 3902 | + } |
|
| 3903 | 3903 | } |
| 3904 | 3904 | ?> |
@@ -3542,7 +3542,10 @@ discard block |
||
| 3542 | 3542 | // Remove leading hyphens and numbers |
| 3543 | 3543 | $token['name'] = ltrim($token['name'], '-0..9'); |
| 3544 | 3544 | // In theory, this should ever be needed, but just in case |
| 3545 | - if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice |
|
| 3545 | + if ($token['name'] === '') { |
|
| 3546 | + $token['name'] = 'span'; |
|
| 3547 | + } |
|
| 3548 | + // arbitrary generic choice |
|
| 3546 | 3549 | } |
| 3547 | 3550 | |
| 3548 | 3551 | $el = $this->dom->createElement($token['name']); |
@@ -3588,10 +3591,11 @@ discard block |
||
| 3588 | 3591 | } |
| 3589 | 3592 | } |
| 3590 | 3593 | |
| 3591 | - if(isset($table) && $this->foster_parent->isSameNode($table->parentNode)) |
|
| 3592 | - $this->foster_parent->insertBefore($node, $table); |
|
| 3593 | - else |
|
| 3594 | - $this->foster_parent->appendChild($node); |
|
| 3594 | + if(isset($table) && $this->foster_parent->isSameNode($table->parentNode)) { |
|
| 3595 | + $this->foster_parent->insertBefore($node, $table); |
|
| 3596 | + } else { |
|
| 3597 | + $this->foster_parent->appendChild($node); |
|
| 3598 | + } |
|
| 3595 | 3599 | |
| 3596 | 3600 | $this->foster_parent = null; |
| 3597 | 3601 | } |
@@ -3754,17 +3758,15 @@ discard block |
||
| 3754 | 3758 | |
| 3755 | 3759 | private function getElementCategory($node) { |
| 3756 | 3760 | $name = $node->tagName; |
| 3757 | - if(in_array($name, $this->special)) |
|
| 3758 | - return self::SPECIAL; |
|
| 3759 | - |
|
| 3760 | - elseif(in_array($name, $this->scoping)) |
|
| 3761 | - return self::SCOPING; |
|
| 3762 | - |
|
| 3763 | - elseif(in_array($name, $this->formatting)) |
|
| 3764 | - return self::FORMATTING; |
|
| 3765 | - |
|
| 3766 | - else |
|
| 3767 | - return self::PHRASING; |
|
| 3761 | + if(in_array($name, $this->special)) { |
|
| 3762 | + return self::SPECIAL; |
|
| 3763 | + } elseif(in_array($name, $this->scoping)) { |
|
| 3764 | + return self::SCOPING; |
|
| 3765 | + } elseif(in_array($name, $this->formatting)) { |
|
| 3766 | + return self::FORMATTING; |
|
| 3767 | + } else { |
|
| 3768 | + return self::PHRASING; |
|
| 3769 | + } |
|
| 3768 | 3770 | } |
| 3769 | 3771 | |
| 3770 | 3772 | private function clearStackToTableContext($elements) { |
@@ -69,48 +69,48 @@ discard block |
||
| 69 | 69 | private $token; |
| 70 | 70 | private $content_model; |
| 71 | 71 | private $escape = false; |
| 72 | - private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute', |
|
| 73 | - 'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;', |
|
| 74 | - 'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;', |
|
| 75 | - 'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;', |
|
| 76 | - 'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;', |
|
| 77 | - 'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;', |
|
| 78 | - 'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;', |
|
| 79 | - 'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;', |
|
| 80 | - 'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;', |
|
| 81 | - 'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN', |
|
| 82 | - 'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;', |
|
| 83 | - 'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;', |
|
| 84 | - 'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig', |
|
| 85 | - 'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;', |
|
| 86 | - 'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;', |
|
| 87 | - 'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil', |
|
| 88 | - 'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;', |
|
| 89 | - 'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;', |
|
| 90 | - 'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;', |
|
| 91 | - 'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth', |
|
| 92 | - 'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12', |
|
| 93 | - 'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt', |
|
| 94 | - 'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc', |
|
| 95 | - 'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;', |
|
| 96 | - 'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;', |
|
| 97 | - 'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;', |
|
| 98 | - 'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro', |
|
| 99 | - 'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;', |
|
| 100 | - 'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;', |
|
| 101 | - 'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;', |
|
| 102 | - 'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash', |
|
| 103 | - 'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;', |
|
| 104 | - 'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;', |
|
| 105 | - 'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;', |
|
| 106 | - 'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;', |
|
| 107 | - 'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;', |
|
| 108 | - 'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;', |
|
| 109 | - 'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;', |
|
| 110 | - 'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;', |
|
| 111 | - 'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc', |
|
| 112 | - 'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;', |
|
| 113 | - 'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;'); |
|
| 72 | + private $entities = array('AElig;', 'AElig', 'AMP;', 'AMP', 'Aacute;', 'Aacute', |
|
| 73 | + 'Acirc;', 'Acirc', 'Agrave;', 'Agrave', 'Alpha;', 'Aring;', 'Aring', 'Atilde;', |
|
| 74 | + 'Atilde', 'Auml;', 'Auml', 'Beta;', 'COPY;', 'COPY', 'Ccedil;', 'Ccedil', 'Chi;', |
|
| 75 | + 'Dagger;', 'Delta;', 'ETH;', 'ETH', 'Eacute;', 'Eacute', 'Ecirc;', 'Ecirc', 'Egrave;', |
|
| 76 | + 'Egrave', 'Epsilon;', 'Eta;', 'Euml;', 'Euml', 'GT;', 'GT', 'Gamma;', 'Iacute;', |
|
| 77 | + 'Iacute', 'Icirc;', 'Icirc', 'Igrave;', 'Igrave', 'Iota;', 'Iuml;', 'Iuml', 'Kappa;', |
|
| 78 | + 'LT;', 'LT', 'Lambda;', 'Mu;', 'Ntilde;', 'Ntilde', 'Nu;', 'OElig;', 'Oacute;', |
|
| 79 | + 'Oacute', 'Ocirc;', 'Ocirc', 'Ograve;', 'Ograve', 'Omega;', 'Omicron;', 'Oslash;', |
|
| 80 | + 'Oslash', 'Otilde;', 'Otilde', 'Ouml;', 'Ouml', 'Phi;', 'Pi;', 'Prime;', 'Psi;', |
|
| 81 | + 'QUOT;', 'QUOT', 'REG;', 'REG', 'Rho;', 'Scaron;', 'Sigma;', 'THORN;', 'THORN', |
|
| 82 | + 'TRADE;', 'Tau;', 'Theta;', 'Uacute;', 'Uacute', 'Ucirc;', 'Ucirc', 'Ugrave;', |
|
| 83 | + 'Ugrave', 'Upsilon;', 'Uuml;', 'Uuml', 'Xi;', 'Yacute;', 'Yacute', 'Yuml;', 'Zeta;', |
|
| 84 | + 'aacute;', 'aacute', 'acirc;', 'acirc', 'acute;', 'acute', 'aelig;', 'aelig', |
|
| 85 | + 'agrave;', 'agrave', 'alefsym;', 'alpha;', 'amp;', 'amp', 'and;', 'ang;', 'apos;', |
|
| 86 | + 'aring;', 'aring', 'asymp;', 'atilde;', 'atilde', 'auml;', 'auml', 'bdquo;', 'beta;', |
|
| 87 | + 'brvbar;', 'brvbar', 'bull;', 'cap;', 'ccedil;', 'ccedil', 'cedil;', 'cedil', |
|
| 88 | + 'cent;', 'cent', 'chi;', 'circ;', 'clubs;', 'cong;', 'copy;', 'copy', 'crarr;', |
|
| 89 | + 'cup;', 'curren;', 'curren', 'dArr;', 'dagger;', 'darr;', 'deg;', 'deg', 'delta;', |
|
| 90 | + 'diams;', 'divide;', 'divide', 'eacute;', 'eacute', 'ecirc;', 'ecirc', 'egrave;', |
|
| 91 | + 'egrave', 'empty;', 'emsp;', 'ensp;', 'epsilon;', 'equiv;', 'eta;', 'eth;', 'eth', |
|
| 92 | + 'euml;', 'euml', 'euro;', 'exist;', 'fnof;', 'forall;', 'frac12;', 'frac12', |
|
| 93 | + 'frac14;', 'frac14', 'frac34;', 'frac34', 'frasl;', 'gamma;', 'ge;', 'gt;', 'gt', |
|
| 94 | + 'hArr;', 'harr;', 'hearts;', 'hellip;', 'iacute;', 'iacute', 'icirc;', 'icirc', |
|
| 95 | + 'iexcl;', 'iexcl', 'igrave;', 'igrave', 'image;', 'infin;', 'int;', 'iota;', |
|
| 96 | + 'iquest;', 'iquest', 'isin;', 'iuml;', 'iuml', 'kappa;', 'lArr;', 'lambda;', 'lang;', |
|
| 97 | + 'laquo;', 'laquo', 'larr;', 'lceil;', 'ldquo;', 'le;', 'lfloor;', 'lowast;', 'loz;', |
|
| 98 | + 'lrm;', 'lsaquo;', 'lsquo;', 'lt;', 'lt', 'macr;', 'macr', 'mdash;', 'micro;', 'micro', |
|
| 99 | + 'middot;', 'middot', 'minus;', 'mu;', 'nabla;', 'nbsp;', 'nbsp', 'ndash;', 'ne;', |
|
| 100 | + 'ni;', 'not;', 'not', 'notin;', 'nsub;', 'ntilde;', 'ntilde', 'nu;', 'oacute;', |
|
| 101 | + 'oacute', 'ocirc;', 'ocirc', 'oelig;', 'ograve;', 'ograve', 'oline;', 'omega;', |
|
| 102 | + 'omicron;', 'oplus;', 'or;', 'ordf;', 'ordf', 'ordm;', 'ordm', 'oslash;', 'oslash', |
|
| 103 | + 'otilde;', 'otilde', 'otimes;', 'ouml;', 'ouml', 'para;', 'para', 'part;', 'permil;', |
|
| 104 | + 'perp;', 'phi;', 'pi;', 'piv;', 'plusmn;', 'plusmn', 'pound;', 'pound', 'prime;', |
|
| 105 | + 'prod;', 'prop;', 'psi;', 'quot;', 'quot', 'rArr;', 'radic;', 'rang;', 'raquo;', |
|
| 106 | + 'raquo', 'rarr;', 'rceil;', 'rdquo;', 'real;', 'reg;', 'reg', 'rfloor;', 'rho;', |
|
| 107 | + 'rlm;', 'rsaquo;', 'rsquo;', 'sbquo;', 'scaron;', 'sdot;', 'sect;', 'sect', 'shy;', |
|
| 108 | + 'shy', 'sigma;', 'sigmaf;', 'sim;', 'spades;', 'sub;', 'sube;', 'sum;', 'sup1;', |
|
| 109 | + 'sup1', 'sup2;', 'sup2', 'sup3;', 'sup3', 'sup;', 'supe;', 'szlig;', 'szlig', 'tau;', |
|
| 110 | + 'there4;', 'theta;', 'thetasym;', 'thinsp;', 'thorn;', 'thorn', 'tilde;', 'times;', |
|
| 111 | + 'times', 'trade;', 'uArr;', 'uacute;', 'uacute', 'uarr;', 'ucirc;', 'ucirc', |
|
| 112 | + 'ugrave;', 'ugrave', 'uml;', 'uml', 'upsih;', 'upsilon;', 'uuml;', 'uuml', 'weierp;', |
|
| 113 | + 'xi;', 'yacute;', 'yacute', 'yen;', 'yen', 'yuml;', 'yuml', 'zeta;', 'zwj;', 'zwnj;'); |
|
| 114 | 114 | |
| 115 | 115 | const PCDATA = 0; |
| 116 | 116 | const RCDATA = 1; |
@@ -134,7 +134,7 @@ discard block |
||
| 134 | 134 | |
| 135 | 135 | $this->state = 'data'; |
| 136 | 136 | |
| 137 | - while($this->state !== null) { |
|
| 137 | + while ($this->state !== null) { |
|
| 138 | 138 | $this->{$this->state.'State'}(); |
| 139 | 139 | } |
| 140 | 140 | } |
@@ -150,8 +150,8 @@ discard block |
||
| 150 | 150 | } |
| 151 | 151 | |
| 152 | 152 | private function character($s, $l = 0) { |
| 153 | - if($s + $l < $this->EOF) { |
|
| 154 | - if($l === 0) { |
|
| 153 | + if ($s + $l < $this->EOF) { |
|
| 154 | + if ($l === 0) { |
|
| 155 | 155 | return $this->data[$s]; |
| 156 | 156 | } else { |
| 157 | 157 | return substr($this->data, $s, $l); |
@@ -168,21 +168,21 @@ discard block |
||
| 168 | 168 | $this->char++; |
| 169 | 169 | $char = $this->char(); |
| 170 | 170 | |
| 171 | - if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { |
|
| 171 | + if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { |
|
| 172 | 172 | /* U+0026 AMPERSAND (&) |
| 173 | 173 | When the content model flag is set to one of the PCDATA or RCDATA |
| 174 | 174 | states: switch to the entity data state. Otherwise: treat it as per |
| 175 | 175 | the "anything else" entry below. */ |
| 176 | 176 | $this->state = 'entityData'; |
| 177 | 177 | |
| 178 | - } elseif($char === '-') { |
|
| 178 | + } elseif ($char === '-') { |
|
| 179 | 179 | /* If the content model flag is set to either the RCDATA state or |
| 180 | 180 | the CDATA state, and the escape flag is false, and there are at |
| 181 | 181 | least three characters before this one in the input stream, and the |
| 182 | 182 | last four characters in the input stream, including this one, are |
| 183 | 183 | U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS, |
| 184 | 184 | and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */ |
| 185 | - if(($this->content_model === self::RCDATA || $this->content_model === |
|
| 185 | + if (($this->content_model === self::RCDATA || $this->content_model === |
|
| 186 | 186 | self::CDATA) && $this->escape === false && |
| 187 | 187 | $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') { |
| 188 | 188 | $this->escape = true; |
@@ -196,7 +196,7 @@ discard block |
||
| 196 | 196 | )); |
| 197 | 197 | |
| 198 | 198 | /* U+003C LESS-THAN SIGN (<) */ |
| 199 | - } elseif($char === '<' && ($this->content_model === self::PCDATA || |
|
| 199 | + } elseif ($char === '<' && ($this->content_model === self::PCDATA || |
|
| 200 | 200 | (($this->content_model === self::RCDATA || |
| 201 | 201 | $this->content_model === self::CDATA) && $this->escape === false))) { |
| 202 | 202 | /* When the content model flag is set to the PCDATA state: switch |
@@ -210,13 +210,13 @@ discard block |
||
| 210 | 210 | $this->state = 'tagOpen'; |
| 211 | 211 | |
| 212 | 212 | /* U+003E GREATER-THAN SIGN (>) */ |
| 213 | - } elseif($char === '>') { |
|
| 213 | + } elseif ($char === '>') { |
|
| 214 | 214 | /* If the content model flag is set to either the RCDATA state or |
| 215 | 215 | the CDATA state, and the escape flag is true, and the last three |
| 216 | 216 | characters in the input stream including this one are U+002D |
| 217 | 217 | HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"), |
| 218 | 218 | set the escape flag to false. */ |
| 219 | - if(($this->content_model === self::RCDATA || |
|
| 219 | + if (($this->content_model === self::RCDATA || |
|
| 220 | 220 | $this->content_model === self::CDATA) && $this->escape === true && |
| 221 | 221 | $this->character($this->char, 3) === '-->') { |
| 222 | 222 | $this->escape = false; |
@@ -229,12 +229,12 @@ discard block |
||
| 229 | 229 | 'data' => $char |
| 230 | 230 | )); |
| 231 | 231 | |
| 232 | - } elseif($this->char === $this->EOF) { |
|
| 232 | + } elseif ($this->char === $this->EOF) { |
|
| 233 | 233 | /* EOF |
| 234 | 234 | Emit an end-of-file token. */ |
| 235 | 235 | $this->EOF(); |
| 236 | 236 | |
| 237 | - } elseif($this->content_model === self::PLAINTEXT) { |
|
| 237 | + } elseif ($this->content_model === self::PLAINTEXT) { |
|
| 238 | 238 | /* When the content model flag is set to the PLAINTEXT state |
| 239 | 239 | THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of |
| 240 | 240 | the text and emit it as a character token. */ |
@@ -280,7 +280,7 @@ discard block |
||
| 280 | 280 | } |
| 281 | 281 | |
| 282 | 282 | private function tagOpenState() { |
| 283 | - switch($this->content_model) { |
|
| 283 | + switch ($this->content_model) { |
|
| 284 | 284 | case self::RCDATA: |
| 285 | 285 | case self::CDATA: |
| 286 | 286 | /* If the next input character is a U+002F SOLIDUS (/) character, |
@@ -288,7 +288,7 @@ discard block |
||
| 288 | 288 | input character is not a U+002F SOLIDUS (/) character, emit a |
| 289 | 289 | U+003C LESS-THAN SIGN character token and switch to the data |
| 290 | 290 | state to process the next input character. */ |
| 291 | - if($this->character($this->char + 1) === '/') { |
|
| 291 | + if ($this->character($this->char + 1) === '/') { |
|
| 292 | 292 | $this->char++; |
| 293 | 293 | $this->state = 'closeTagOpen'; |
| 294 | 294 | |
@@ -308,17 +308,17 @@ discard block |
||
| 308 | 308 | $this->char++; |
| 309 | 309 | $char = $this->char(); |
| 310 | 310 | |
| 311 | - if($char === '!') { |
|
| 311 | + if ($char === '!') { |
|
| 312 | 312 | /* U+0021 EXCLAMATION MARK (!) |
| 313 | 313 | Switch to the markup declaration open state. */ |
| 314 | 314 | $this->state = 'markupDeclarationOpen'; |
| 315 | 315 | |
| 316 | - } elseif($char === '/') { |
|
| 316 | + } elseif ($char === '/') { |
|
| 317 | 317 | /* U+002F SOLIDUS (/) |
| 318 | 318 | Switch to the close tag open state. */ |
| 319 | 319 | $this->state = 'closeTagOpen'; |
| 320 | 320 | |
| 321 | - } elseif(preg_match('/^[A-Za-z]$/', $char)) { |
|
| 321 | + } elseif (preg_match('/^[A-Za-z]$/', $char)) { |
|
| 322 | 322 | /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z |
| 323 | 323 | Create a new start tag token, set its tag name to the lowercase |
| 324 | 324 | version of the input character (add 0x0020 to the character's code |
@@ -332,7 +332,7 @@ discard block |
||
| 332 | 332 | |
| 333 | 333 | $this->state = 'tagName'; |
| 334 | 334 | |
| 335 | - } elseif($char === '>') { |
|
| 335 | + } elseif ($char === '>') { |
|
| 336 | 336 | /* U+003E GREATER-THAN SIGN (>) |
| 337 | 337 | Parse error. Emit a U+003C LESS-THAN SIGN character token and a |
| 338 | 338 | U+003E GREATER-THAN SIGN character token. Switch to the data state. */ |
@@ -343,7 +343,7 @@ discard block |
||
| 343 | 343 | |
| 344 | 344 | $this->state = 'data'; |
| 345 | 345 | |
| 346 | - } elseif($char === '?') { |
|
| 346 | + } elseif ($char === '?') { |
|
| 347 | 347 | /* U+003F QUESTION MARK (?) |
| 348 | 348 | Parse error. Switch to the bogus comment state. */ |
| 349 | 349 | $this->state = 'bogusComment'; |
@@ -368,7 +368,7 @@ discard block |
||
| 368 | 368 | $next_node = strtolower($this->characters('A-Za-z', $this->char + 1)); |
| 369 | 369 | $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName; |
| 370 | 370 | |
| 371 | - if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && |
|
| 371 | + if (($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && |
|
| 372 | 372 | (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/', |
| 373 | 373 | $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) { |
| 374 | 374 | /* If the content model flag is set to the RCDATA or CDATA states then |
@@ -400,7 +400,7 @@ discard block |
||
| 400 | 400 | $this->char++; |
| 401 | 401 | $char = $this->char(); |
| 402 | 402 | |
| 403 | - if(preg_match('/^[A-Za-z]$/', $char)) { |
|
| 403 | + if (preg_match('/^[A-Za-z]$/', $char)) { |
|
| 404 | 404 | /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z |
| 405 | 405 | Create a new end tag token, set its tag name to the lowercase version |
| 406 | 406 | of the input character (add 0x0020 to the character's code point), then |
@@ -413,12 +413,12 @@ discard block |
||
| 413 | 413 | |
| 414 | 414 | $this->state = 'tagName'; |
| 415 | 415 | |
| 416 | - } elseif($char === '>') { |
|
| 416 | + } elseif ($char === '>') { |
|
| 417 | 417 | /* U+003E GREATER-THAN SIGN (>) |
| 418 | 418 | Parse error. Switch to the data state. */ |
| 419 | 419 | $this->state = 'data'; |
| 420 | 420 | |
| 421 | - } elseif($this->char === $this->EOF) { |
|
| 421 | + } elseif ($this->char === $this->EOF) { |
|
| 422 | 422 | /* EOF |
| 423 | 423 | Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F |
| 424 | 424 | SOLIDUS character token. Reconsume the EOF character in the data state. */ |
@@ -442,7 +442,7 @@ discard block |
||
| 442 | 442 | $this->char++; |
| 443 | 443 | $char = $this->character($this->char); |
| 444 | 444 | |
| 445 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 445 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 446 | 446 | /* U+0009 CHARACTER TABULATION |
| 447 | 447 | U+000A LINE FEED (LF) |
| 448 | 448 | U+000B LINE TABULATION |
@@ -451,13 +451,13 @@ discard block |
||
| 451 | 451 | Switch to the before attribute name state. */ |
| 452 | 452 | $this->state = 'beforeAttributeName'; |
| 453 | 453 | |
| 454 | - } elseif($char === '>') { |
|
| 454 | + } elseif ($char === '>') { |
|
| 455 | 455 | /* U+003E GREATER-THAN SIGN (>) |
| 456 | 456 | Emit the current tag token. Switch to the data state. */ |
| 457 | 457 | $this->emitToken($this->token); |
| 458 | 458 | $this->state = 'data'; |
| 459 | 459 | |
| 460 | - } elseif($this->char === $this->EOF) { |
|
| 460 | + } elseif ($this->char === $this->EOF) { |
|
| 461 | 461 | /* EOF |
| 462 | 462 | Parse error. Emit the current tag token. Reconsume the EOF |
| 463 | 463 | character in the data state. */ |
@@ -466,7 +466,7 @@ discard block |
||
| 466 | 466 | $this->char--; |
| 467 | 467 | $this->state = 'data'; |
| 468 | 468 | |
| 469 | - } elseif($char === '/') { |
|
| 469 | + } elseif ($char === '/') { |
|
| 470 | 470 | /* U+002F SOLIDUS (/) |
| 471 | 471 | Parse error unless this is a permitted slash. Switch to the before |
| 472 | 472 | attribute name state. */ |
@@ -486,7 +486,7 @@ discard block |
||
| 486 | 486 | $this->char++; |
| 487 | 487 | $char = $this->character($this->char); |
| 488 | 488 | |
| 489 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 489 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 490 | 490 | /* U+0009 CHARACTER TABULATION |
| 491 | 491 | U+000A LINE FEED (LF) |
| 492 | 492 | U+000B LINE TABULATION |
@@ -495,19 +495,19 @@ discard block |
||
| 495 | 495 | Stay in the before attribute name state. */ |
| 496 | 496 | $this->state = 'beforeAttributeName'; |
| 497 | 497 | |
| 498 | - } elseif($char === '>') { |
|
| 498 | + } elseif ($char === '>') { |
|
| 499 | 499 | /* U+003E GREATER-THAN SIGN (>) |
| 500 | 500 | Emit the current tag token. Switch to the data state. */ |
| 501 | 501 | $this->emitToken($this->token); |
| 502 | 502 | $this->state = 'data'; |
| 503 | 503 | |
| 504 | - } elseif($char === '/') { |
|
| 504 | + } elseif ($char === '/') { |
|
| 505 | 505 | /* U+002F SOLIDUS (/) |
| 506 | 506 | Parse error unless this is a permitted slash. Stay in the before |
| 507 | 507 | attribute name state. */ |
| 508 | 508 | $this->state = 'beforeAttributeName'; |
| 509 | 509 | |
| 510 | - } elseif($this->char === $this->EOF) { |
|
| 510 | + } elseif ($this->char === $this->EOF) { |
|
| 511 | 511 | /* EOF |
| 512 | 512 | Parse error. Emit the current tag token. Reconsume the EOF |
| 513 | 513 | character in the data state. */ |
@@ -535,7 +535,7 @@ discard block |
||
| 535 | 535 | $this->char++; |
| 536 | 536 | $char = $this->character($this->char); |
| 537 | 537 | |
| 538 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 538 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 539 | 539 | /* U+0009 CHARACTER TABULATION |
| 540 | 540 | U+000A LINE FEED (LF) |
| 541 | 541 | U+000B LINE TABULATION |
@@ -544,24 +544,24 @@ discard block |
||
| 544 | 544 | Stay in the before attribute name state. */ |
| 545 | 545 | $this->state = 'afterAttributeName'; |
| 546 | 546 | |
| 547 | - } elseif($char === '=') { |
|
| 547 | + } elseif ($char === '=') { |
|
| 548 | 548 | /* U+003D EQUALS SIGN (=) |
| 549 | 549 | Switch to the before attribute value state. */ |
| 550 | 550 | $this->state = 'beforeAttributeValue'; |
| 551 | 551 | |
| 552 | - } elseif($char === '>') { |
|
| 552 | + } elseif ($char === '>') { |
|
| 553 | 553 | /* U+003E GREATER-THAN SIGN (>) |
| 554 | 554 | Emit the current tag token. Switch to the data state. */ |
| 555 | 555 | $this->emitToken($this->token); |
| 556 | 556 | $this->state = 'data'; |
| 557 | 557 | |
| 558 | - } elseif($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 558 | + } elseif ($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 559 | 559 | /* U+002F SOLIDUS (/) |
| 560 | 560 | Parse error unless this is a permitted slash. Switch to the before |
| 561 | 561 | attribute name state. */ |
| 562 | 562 | $this->state = 'beforeAttributeName'; |
| 563 | 563 | |
| 564 | - } elseif($this->char === $this->EOF) { |
|
| 564 | + } elseif ($this->char === $this->EOF) { |
|
| 565 | 565 | /* EOF |
| 566 | 566 | Parse error. Emit the current tag token. Reconsume the EOF |
| 567 | 567 | character in the data state. */ |
@@ -586,7 +586,7 @@ discard block |
||
| 586 | 586 | $this->char++; |
| 587 | 587 | $char = $this->character($this->char); |
| 588 | 588 | |
| 589 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 589 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 590 | 590 | /* U+0009 CHARACTER TABULATION |
| 591 | 591 | U+000A LINE FEED (LF) |
| 592 | 592 | U+000B LINE TABULATION |
@@ -595,24 +595,24 @@ discard block |
||
| 595 | 595 | Stay in the after attribute name state. */ |
| 596 | 596 | $this->state = 'afterAttributeName'; |
| 597 | 597 | |
| 598 | - } elseif($char === '=') { |
|
| 598 | + } elseif ($char === '=') { |
|
| 599 | 599 | /* U+003D EQUALS SIGN (=) |
| 600 | 600 | Switch to the before attribute value state. */ |
| 601 | 601 | $this->state = 'beforeAttributeValue'; |
| 602 | 602 | |
| 603 | - } elseif($char === '>') { |
|
| 603 | + } elseif ($char === '>') { |
|
| 604 | 604 | /* U+003E GREATER-THAN SIGN (>) |
| 605 | 605 | Emit the current tag token. Switch to the data state. */ |
| 606 | 606 | $this->emitToken($this->token); |
| 607 | 607 | $this->state = 'data'; |
| 608 | 608 | |
| 609 | - } elseif($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 609 | + } elseif ($char === '/' && $this->character($this->char + 1) !== '>') { |
|
| 610 | 610 | /* U+002F SOLIDUS (/) |
| 611 | 611 | Parse error unless this is a permitted slash. Switch to the |
| 612 | 612 | before attribute name state. */ |
| 613 | 613 | $this->state = 'beforeAttributeName'; |
| 614 | 614 | |
| 615 | - } elseif($this->char === $this->EOF) { |
|
| 615 | + } elseif ($this->char === $this->EOF) { |
|
| 616 | 616 | /* EOF |
| 617 | 617 | Parse error. Emit the current tag token. Reconsume the EOF |
| 618 | 618 | character in the data state. */ |
@@ -640,7 +640,7 @@ discard block |
||
| 640 | 640 | $this->char++; |
| 641 | 641 | $char = $this->character($this->char); |
| 642 | 642 | |
| 643 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 643 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 644 | 644 | /* U+0009 CHARACTER TABULATION |
| 645 | 645 | U+000A LINE FEED (LF) |
| 646 | 646 | U+000B LINE TABULATION |
@@ -649,24 +649,24 @@ discard block |
||
| 649 | 649 | Stay in the before attribute value state. */ |
| 650 | 650 | $this->state = 'beforeAttributeValue'; |
| 651 | 651 | |
| 652 | - } elseif($char === '"') { |
|
| 652 | + } elseif ($char === '"') { |
|
| 653 | 653 | /* U+0022 QUOTATION MARK (") |
| 654 | 654 | Switch to the attribute value (double-quoted) state. */ |
| 655 | 655 | $this->state = 'attributeValueDoubleQuoted'; |
| 656 | 656 | |
| 657 | - } elseif($char === '&') { |
|
| 657 | + } elseif ($char === '&') { |
|
| 658 | 658 | /* U+0026 AMPERSAND (&) |
| 659 | 659 | Switch to the attribute value (unquoted) state and reconsume |
| 660 | 660 | this input character. */ |
| 661 | 661 | $this->char--; |
| 662 | 662 | $this->state = 'attributeValueUnquoted'; |
| 663 | 663 | |
| 664 | - } elseif($char === '\'') { |
|
| 664 | + } elseif ($char === '\'') { |
|
| 665 | 665 | /* U+0027 APOSTROPHE (') |
| 666 | 666 | Switch to the attribute value (single-quoted) state. */ |
| 667 | 667 | $this->state = 'attributeValueSingleQuoted'; |
| 668 | 668 | |
| 669 | - } elseif($char === '>') { |
|
| 669 | + } elseif ($char === '>') { |
|
| 670 | 670 | /* U+003E GREATER-THAN SIGN (>) |
| 671 | 671 | Emit the current tag token. Switch to the data state. */ |
| 672 | 672 | $this->emitToken($this->token); |
@@ -688,17 +688,17 @@ discard block |
||
| 688 | 688 | $this->char++; |
| 689 | 689 | $char = $this->character($this->char); |
| 690 | 690 | |
| 691 | - if($char === '"') { |
|
| 691 | + if ($char === '"') { |
|
| 692 | 692 | /* U+0022 QUOTATION MARK (") |
| 693 | 693 | Switch to the before attribute name state. */ |
| 694 | 694 | $this->state = 'beforeAttributeName'; |
| 695 | 695 | |
| 696 | - } elseif($char === '&') { |
|
| 696 | + } elseif ($char === '&') { |
|
| 697 | 697 | /* U+0026 AMPERSAND (&) |
| 698 | 698 | Switch to the entity in attribute value state. */ |
| 699 | 699 | $this->entityInAttributeValueState('double'); |
| 700 | 700 | |
| 701 | - } elseif($this->char === $this->EOF) { |
|
| 701 | + } elseif ($this->char === $this->EOF) { |
|
| 702 | 702 | /* EOF |
| 703 | 703 | Parse error. Emit the current tag token. Reconsume the character |
| 704 | 704 | in the data state. */ |
@@ -723,17 +723,17 @@ discard block |
||
| 723 | 723 | $this->char++; |
| 724 | 724 | $char = $this->character($this->char); |
| 725 | 725 | |
| 726 | - if($char === '\'') { |
|
| 726 | + if ($char === '\'') { |
|
| 727 | 727 | /* U+0022 QUOTATION MARK (') |
| 728 | 728 | Switch to the before attribute name state. */ |
| 729 | 729 | $this->state = 'beforeAttributeName'; |
| 730 | 730 | |
| 731 | - } elseif($char === '&') { |
|
| 731 | + } elseif ($char === '&') { |
|
| 732 | 732 | /* U+0026 AMPERSAND (&) |
| 733 | 733 | Switch to the entity in attribute value state. */ |
| 734 | 734 | $this->entityInAttributeValueState('single'); |
| 735 | 735 | |
| 736 | - } elseif($this->char === $this->EOF) { |
|
| 736 | + } elseif ($this->char === $this->EOF) { |
|
| 737 | 737 | /* EOF |
| 738 | 738 | Parse error. Emit the current tag token. Reconsume the character |
| 739 | 739 | in the data state. */ |
@@ -758,7 +758,7 @@ discard block |
||
| 758 | 758 | $this->char++; |
| 759 | 759 | $char = $this->character($this->char); |
| 760 | 760 | |
| 761 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 761 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 762 | 762 | /* U+0009 CHARACTER TABULATION |
| 763 | 763 | U+000A LINE FEED (LF) |
| 764 | 764 | U+000B LINE TABULATION |
@@ -767,12 +767,12 @@ discard block |
||
| 767 | 767 | Switch to the before attribute name state. */ |
| 768 | 768 | $this->state = 'beforeAttributeName'; |
| 769 | 769 | |
| 770 | - } elseif($char === '&') { |
|
| 770 | + } elseif ($char === '&') { |
|
| 771 | 771 | /* U+0026 AMPERSAND (&) |
| 772 | 772 | Switch to the entity in attribute value state. */ |
| 773 | 773 | $this->entityInAttributeValueState(); |
| 774 | 774 | |
| 775 | - } elseif($char === '>') { |
|
| 775 | + } elseif ($char === '>') { |
|
| 776 | 776 | /* U+003E GREATER-THAN SIGN (>) |
| 777 | 777 | Emit the current tag token. Switch to the data state. */ |
| 778 | 778 | $this->emitToken($this->token); |
@@ -825,7 +825,7 @@ discard block |
||
| 825 | 825 | $this->state = 'data'; |
| 826 | 826 | |
| 827 | 827 | /* If the end of the file was reached, reconsume the EOF character. */ |
| 828 | - if($this->char === $this->EOF) { |
|
| 828 | + if ($this->char === $this->EOF) { |
|
| 829 | 829 | $this->char = $this->EOF - 1; |
| 830 | 830 | } |
| 831 | 831 | } |
@@ -834,7 +834,7 @@ discard block |
||
| 834 | 834 | /* If the next two characters are both U+002D HYPHEN-MINUS (-) |
| 835 | 835 | characters, consume those two characters, create a comment token whose |
| 836 | 836 | data is the empty string, and switch to the comment state. */ |
| 837 | - if($this->character($this->char + 1, 2) === '--') { |
|
| 837 | + if ($this->character($this->char + 1, 2) === '--') { |
|
| 838 | 838 | $this->char += 2; |
| 839 | 839 | $this->state = 'comment'; |
| 840 | 840 | $this->token = array( |
@@ -845,7 +845,7 @@ discard block |
||
| 845 | 845 | /* Otherwise if the next seven chacacters are a case-insensitive match |
| 846 | 846 | for the word "DOCTYPE", then consume those characters and switch to the |
| 847 | 847 | DOCTYPE state. */ |
| 848 | - } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') { |
|
| 848 | + } elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') { |
|
| 849 | 849 | $this->char += 7; |
| 850 | 850 | $this->state = 'doctype'; |
| 851 | 851 | |
@@ -864,12 +864,12 @@ discard block |
||
| 864 | 864 | $char = $this->char(); |
| 865 | 865 | |
| 866 | 866 | /* U+002D HYPHEN-MINUS (-) */ |
| 867 | - if($char === '-') { |
|
| 867 | + if ($char === '-') { |
|
| 868 | 868 | /* Switch to the comment dash state */ |
| 869 | 869 | $this->state = 'commentDash'; |
| 870 | 870 | |
| 871 | 871 | /* EOF */ |
| 872 | - } elseif($this->char === $this->EOF) { |
|
| 872 | + } elseif ($this->char === $this->EOF) { |
|
| 873 | 873 | /* Parse error. Emit the comment token. Reconsume the EOF character |
| 874 | 874 | in the data state. */ |
| 875 | 875 | $this->emitToken($this->token); |
@@ -890,12 +890,12 @@ discard block |
||
| 890 | 890 | $char = $this->char(); |
| 891 | 891 | |
| 892 | 892 | /* U+002D HYPHEN-MINUS (-) */ |
| 893 | - if($char === '-') { |
|
| 893 | + if ($char === '-') { |
|
| 894 | 894 | /* Switch to the comment end state */ |
| 895 | 895 | $this->state = 'commentEnd'; |
| 896 | 896 | |
| 897 | 897 | /* EOF */ |
| 898 | - } elseif($this->char === $this->EOF) { |
|
| 898 | + } elseif ($this->char === $this->EOF) { |
|
| 899 | 899 | /* Parse error. Emit the comment token. Reconsume the EOF character |
| 900 | 900 | in the data state. */ |
| 901 | 901 | $this->emitToken($this->token); |
@@ -916,14 +916,14 @@ discard block |
||
| 916 | 916 | $this->char++; |
| 917 | 917 | $char = $this->char(); |
| 918 | 918 | |
| 919 | - if($char === '>') { |
|
| 919 | + if ($char === '>') { |
|
| 920 | 920 | $this->emitToken($this->token); |
| 921 | 921 | $this->state = 'data'; |
| 922 | 922 | |
| 923 | - } elseif($char === '-') { |
|
| 923 | + } elseif ($char === '-') { |
|
| 924 | 924 | $this->token['data'] .= '-'; |
| 925 | 925 | |
| 926 | - } elseif($this->char === $this->EOF) { |
|
| 926 | + } elseif ($this->char === $this->EOF) { |
|
| 927 | 927 | $this->emitToken($this->token); |
| 928 | 928 | $this->char--; |
| 929 | 929 | $this->state = 'data'; |
@@ -939,7 +939,7 @@ discard block |
||
| 939 | 939 | $this->char++; |
| 940 | 940 | $char = $this->char(); |
| 941 | 941 | |
| 942 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 942 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 943 | 943 | $this->state = 'beforeDoctypeName'; |
| 944 | 944 | |
| 945 | 945 | } else { |
@@ -953,10 +953,10 @@ discard block |
||
| 953 | 953 | $this->char++; |
| 954 | 954 | $char = $this->char(); |
| 955 | 955 | |
| 956 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 956 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 957 | 957 | // Stay in the before DOCTYPE name state. |
| 958 | 958 | |
| 959 | - } elseif(preg_match('/^[a-z]$/', $char)) { |
|
| 959 | + } elseif (preg_match('/^[a-z]$/', $char)) { |
|
| 960 | 960 | $this->token = array( |
| 961 | 961 | 'name' => strtoupper($char), |
| 962 | 962 | 'type' => self::DOCTYPE, |
@@ -965,7 +965,7 @@ discard block |
||
| 965 | 965 | |
| 966 | 966 | $this->state = 'doctypeName'; |
| 967 | 967 | |
| 968 | - } elseif($char === '>') { |
|
| 968 | + } elseif ($char === '>') { |
|
| 969 | 969 | $this->emitToken(array( |
| 970 | 970 | 'name' => null, |
| 971 | 971 | 'type' => self::DOCTYPE, |
@@ -974,7 +974,7 @@ discard block |
||
| 974 | 974 | |
| 975 | 975 | $this->state = 'data'; |
| 976 | 976 | |
| 977 | - } elseif($this->char === $this->EOF) { |
|
| 977 | + } elseif ($this->char === $this->EOF) { |
|
| 978 | 978 | $this->emitToken(array( |
| 979 | 979 | 'name' => null, |
| 980 | 980 | 'type' => self::DOCTYPE, |
@@ -1000,17 +1000,17 @@ discard block |
||
| 1000 | 1000 | $this->char++; |
| 1001 | 1001 | $char = $this->char(); |
| 1002 | 1002 | |
| 1003 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1003 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1004 | 1004 | $this->state = 'AfterDoctypeName'; |
| 1005 | 1005 | |
| 1006 | - } elseif($char === '>') { |
|
| 1006 | + } elseif ($char === '>') { |
|
| 1007 | 1007 | $this->emitToken($this->token); |
| 1008 | 1008 | $this->state = 'data'; |
| 1009 | 1009 | |
| 1010 | - } elseif(preg_match('/^[a-z]$/', $char)) { |
|
| 1010 | + } elseif (preg_match('/^[a-z]$/', $char)) { |
|
| 1011 | 1011 | $this->token['name'] .= strtoupper($char); |
| 1012 | 1012 | |
| 1013 | - } elseif($this->char === $this->EOF) { |
|
| 1013 | + } elseif ($this->char === $this->EOF) { |
|
| 1014 | 1014 | $this->emitToken($this->token); |
| 1015 | 1015 | $this->char--; |
| 1016 | 1016 | $this->state = 'data'; |
@@ -1029,14 +1029,14 @@ discard block |
||
| 1029 | 1029 | $this->char++; |
| 1030 | 1030 | $char = $this->char(); |
| 1031 | 1031 | |
| 1032 | - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1032 | + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { |
|
| 1033 | 1033 | // Stay in the DOCTYPE name state. |
| 1034 | 1034 | |
| 1035 | - } elseif($char === '>') { |
|
| 1035 | + } elseif ($char === '>') { |
|
| 1036 | 1036 | $this->emitToken($this->token); |
| 1037 | 1037 | $this->state = 'data'; |
| 1038 | 1038 | |
| 1039 | - } elseif($this->char === $this->EOF) { |
|
| 1039 | + } elseif ($this->char === $this->EOF) { |
|
| 1040 | 1040 | $this->emitToken($this->token); |
| 1041 | 1041 | $this->char--; |
| 1042 | 1042 | $this->state = 'data'; |
@@ -1052,11 +1052,11 @@ discard block |
||
| 1052 | 1052 | $this->char++; |
| 1053 | 1053 | $char = $this->char(); |
| 1054 | 1054 | |
| 1055 | - if($char === '>') { |
|
| 1055 | + if ($char === '>') { |
|
| 1056 | 1056 | $this->emitToken($this->token); |
| 1057 | 1057 | $this->state = 'data'; |
| 1058 | 1058 | |
| 1059 | - } elseif($this->char === $this->EOF) { |
|
| 1059 | + } elseif ($this->char === $this->EOF) { |
|
| 1060 | 1060 | $this->emitToken($this->token); |
| 1061 | 1061 | $this->char--; |
| 1062 | 1062 | $this->state = 'data'; |
@@ -1075,13 +1075,13 @@ discard block |
||
| 1075 | 1075 | // The behaviour depends on the identity of the next character (the |
| 1076 | 1076 | // one immediately after the U+0026 AMPERSAND character): |
| 1077 | 1077 | |
| 1078 | - switch($this->character($this->char + 1)) { |
|
| 1078 | + switch ($this->character($this->char + 1)) { |
|
| 1079 | 1079 | // U+0023 NUMBER SIGN (#) |
| 1080 | 1080 | case '#': |
| 1081 | 1081 | |
| 1082 | 1082 | // The behaviour further depends on the character after the |
| 1083 | 1083 | // U+0023 NUMBER SIGN: |
| 1084 | - switch($this->character($this->char + 1)) { |
|
| 1084 | + switch ($this->character($this->char + 1)) { |
|
| 1085 | 1085 | // U+0078 LATIN SMALL LETTER X |
| 1086 | 1086 | // U+0058 LATIN CAPITAL LETTER X |
| 1087 | 1087 | case 'x': |
@@ -1124,12 +1124,12 @@ discard block |
||
| 1124 | 1124 | $e_name = $this->characters('0-9A-Za-z;', $this->char + 1); |
| 1125 | 1125 | $len = strlen($e_name); |
| 1126 | 1126 | |
| 1127 | - for($c = 1; $c <= $len; $c++) { |
|
| 1127 | + for ($c = 1; $c <= $len; $c++) { |
|
| 1128 | 1128 | $id = substr($e_name, 0, $c); |
| 1129 | 1129 | $this->char++; |
| 1130 | 1130 | |
| 1131 | - if(in_array($id, $this->entities)) { |
|
| 1132 | - if ($e_name[$c-1] !== ';') { |
|
| 1131 | + if (in_array($id, $this->entities)) { |
|
| 1132 | + if ($e_name[$c - 1] !== ';') { |
|
| 1133 | 1133 | if ($c < $len && $e_name[$c] == ';') { |
| 1134 | 1134 | $this->char++; // consume extra semicolon |
| 1135 | 1135 | } |
@@ -1144,7 +1144,7 @@ discard block |
||
| 1144 | 1144 | break; |
| 1145 | 1145 | } |
| 1146 | 1146 | |
| 1147 | - if(!$cond) { |
|
| 1147 | + if (!$cond) { |
|
| 1148 | 1148 | // If no match can be made, then this is a parse error. No |
| 1149 | 1149 | // characters are consumed, and nothing is returned. |
| 1150 | 1150 | $this->char = $start; |
@@ -1159,10 +1159,10 @@ discard block |
||
| 1159 | 1159 | private function emitToken($token) { |
| 1160 | 1160 | $emit = $this->tree->emitToken($token); |
| 1161 | 1161 | |
| 1162 | - if(is_int($emit)) { |
|
| 1162 | + if (is_int($emit)) { |
|
| 1163 | 1163 | $this->content_model = $emit; |
| 1164 | 1164 | |
| 1165 | - } elseif($token['type'] === self::ENDTAG) { |
|
| 1165 | + } elseif ($token['type'] === self::ENDTAG) { |
|
| 1166 | 1166 | $this->content_model = self::PCDATA; |
| 1167 | 1167 | } |
| 1168 | 1168 | } |
@@ -1187,15 +1187,15 @@ discard block |
||
| 1187 | 1187 | private $head_pointer = null; |
| 1188 | 1188 | private $form_pointer = null; |
| 1189 | 1189 | |
| 1190 | - private $scoping = array('button','caption','html','marquee','object','table','td','th'); |
|
| 1191 | - private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u'); |
|
| 1192 | - private $special = array('address','area','base','basefont','bgsound', |
|
| 1193 | - 'blockquote','body','br','center','col','colgroup','dd','dir','div','dl', |
|
| 1194 | - 'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5', |
|
| 1195 | - 'h6','head','hr','iframe','image','img','input','isindex','li','link', |
|
| 1196 | - 'listing','menu','meta','noembed','noframes','noscript','ol','optgroup', |
|
| 1197 | - 'option','p','param','plaintext','pre','script','select','spacer','style', |
|
| 1198 | - 'tbody','textarea','tfoot','thead','title','tr','ul','wbr'); |
|
| 1190 | + private $scoping = array('button', 'caption', 'html', 'marquee', 'object', 'table', 'td', 'th'); |
|
| 1191 | + private $formatting = array('a', 'b', 'big', 'em', 'font', 'i', 'nobr', 's', 'small', 'strike', 'strong', 'tt', 'u'); |
|
| 1192 | + private $special = array('address', 'area', 'base', 'basefont', 'bgsound', |
|
| 1193 | + 'blockquote', 'body', 'br', 'center', 'col', 'colgroup', 'dd', 'dir', 'div', 'dl', |
|
| 1194 | + 'dt', 'embed', 'fieldset', 'form', 'frame', 'frameset', 'h1', 'h2', 'h3', 'h4', 'h5', |
|
| 1195 | + 'h6', 'head', 'hr', 'iframe', 'image', 'img', 'input', 'isindex', 'li', 'link', |
|
| 1196 | + 'listing', 'menu', 'meta', 'noembed', 'noframes', 'noscript', 'ol', 'optgroup', |
|
| 1197 | + 'option', 'p', 'param', 'plaintext', 'pre', 'script', 'select', 'spacer', 'style', |
|
| 1198 | + 'tbody', 'textarea', 'tfoot', 'thead', 'title', 'tr', 'ul', 'wbr'); |
|
| 1199 | 1199 | |
| 1200 | 1200 | // The different phases. |
| 1201 | 1201 | const INIT_PHASE = 0; |
@@ -1240,7 +1240,7 @@ discard block |
||
| 1240 | 1240 | |
| 1241 | 1241 | // Process tag tokens |
| 1242 | 1242 | public function emitToken($token) { |
| 1243 | - switch($this->phase) { |
|
| 1243 | + switch ($this->phase) { |
|
| 1244 | 1244 | case self::INIT_PHASE: return $this->initPhase($token); break; |
| 1245 | 1245 | case self::ROOT_PHASE: return $this->rootElementPhase($token); break; |
| 1246 | 1246 | case self::MAIN_PHASE: return $this->mainPhase($token); break; |
@@ -1260,7 +1260,7 @@ discard block |
||
| 1260 | 1260 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1261 | 1261 | or U+0020 SPACE |
| 1262 | 1262 | An end-of-file token */ |
| 1263 | - if((isset($token['error']) && $token['error']) || |
|
| 1263 | + if ((isset($token['error']) && $token['error']) || |
|
| 1264 | 1264 | $token['type'] === HTML5::COMMENT || |
| 1265 | 1265 | $token['type'] === HTML5::STARTTAG || |
| 1266 | 1266 | $token['type'] === HTML5::ENDTAG || |
@@ -1276,7 +1276,7 @@ discard block |
||
| 1276 | 1276 | return $this->rootElementPhase($token); |
| 1277 | 1277 | |
| 1278 | 1278 | /* A DOCTYPE token marked as being correct */ |
| 1279 | - } elseif(isset($token['error']) && !$token['error']) { |
|
| 1279 | + } elseif (isset($token['error']) && !$token['error']) { |
|
| 1280 | 1280 | /* Append a DocumentType node to the Document node, with the name |
| 1281 | 1281 | attribute set to the name given in the DOCTYPE token (which will be |
| 1282 | 1282 | "HTML"), and the other attributes specific to DocumentType objects |
@@ -1290,7 +1290,7 @@ discard block |
||
| 1290 | 1290 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 1291 | 1291 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1292 | 1292 | or U+0020 SPACE */ |
| 1293 | - } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/', |
|
| 1293 | + } elseif (isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/', |
|
| 1294 | 1294 | $token['data'])) { |
| 1295 | 1295 | /* Append that character to the Document node. */ |
| 1296 | 1296 | $text = $this->dom->createTextNode($token['data']); |
@@ -1303,11 +1303,11 @@ discard block |
||
| 1303 | 1303 | stage, it must be processed as described in this section. */ |
| 1304 | 1304 | |
| 1305 | 1305 | /* A DOCTYPE token */ |
| 1306 | - if($token['type'] === HTML5::DOCTYPE) { |
|
| 1306 | + if ($token['type'] === HTML5::DOCTYPE) { |
|
| 1307 | 1307 | // Parse error. Ignore the token. |
| 1308 | 1308 | |
| 1309 | 1309 | /* A comment token */ |
| 1310 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1310 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 1311 | 1311 | /* Append a Comment node to the Document object with the data |
| 1312 | 1312 | attribute set to the data given in the comment token. */ |
| 1313 | 1313 | $comment = $this->dom->createComment($token['data']); |
@@ -1316,7 +1316,7 @@ discard block |
||
| 1316 | 1316 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 1317 | 1317 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1318 | 1318 | or U+0020 SPACE */ |
| 1319 | - } elseif($token['type'] === HTML5::CHARACTR && |
|
| 1319 | + } elseif ($token['type'] === HTML5::CHARACTR && |
|
| 1320 | 1320 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 1321 | 1321 | /* Append that character to the Document node. */ |
| 1322 | 1322 | $text = $this->dom->createTextNode($token['data']); |
@@ -1328,7 +1328,7 @@ discard block |
||
| 1328 | 1328 | A start tag token |
| 1329 | 1329 | An end tag token |
| 1330 | 1330 | An end-of-file token */ |
| 1331 | - } elseif(($token['type'] === HTML5::CHARACTR && |
|
| 1331 | + } elseif (($token['type'] === HTML5::CHARACTR && |
|
| 1332 | 1332 | !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || |
| 1333 | 1333 | $token['type'] === HTML5::STARTTAG || |
| 1334 | 1334 | $token['type'] === HTML5::ENDTAG || |
@@ -1349,11 +1349,11 @@ discard block |
||
| 1349 | 1349 | /* Tokens in the main phase must be handled as follows: */ |
| 1350 | 1350 | |
| 1351 | 1351 | /* A DOCTYPE token */ |
| 1352 | - if($token['type'] === HTML5::DOCTYPE) { |
|
| 1352 | + if ($token['type'] === HTML5::DOCTYPE) { |
|
| 1353 | 1353 | // Parse error. Ignore the token. |
| 1354 | 1354 | |
| 1355 | 1355 | /* A start tag token with the tag name "html" */ |
| 1356 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { |
|
| 1356 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { |
|
| 1357 | 1357 | /* If this start tag token was not the first start tag token, then |
| 1358 | 1358 | it is a parse error. */ |
| 1359 | 1359 | |
@@ -1361,21 +1361,21 @@ discard block |
||
| 1361 | 1361 | is already present on the top element of the stack of open elements. |
| 1362 | 1362 | If it is not, add the attribute and its corresponding value to that |
| 1363 | 1363 | element. */ |
| 1364 | - foreach($token['attr'] as $attr) { |
|
| 1365 | - if(!$this->stack[0]->hasAttribute($attr['name'])) { |
|
| 1364 | + foreach ($token['attr'] as $attr) { |
|
| 1365 | + if (!$this->stack[0]->hasAttribute($attr['name'])) { |
|
| 1366 | 1366 | $this->stack[0]->setAttribute($attr['name'], $attr['value']); |
| 1367 | 1367 | } |
| 1368 | 1368 | } |
| 1369 | 1369 | |
| 1370 | 1370 | /* An end-of-file token */ |
| 1371 | - } elseif($token['type'] === HTML5::EOF) { |
|
| 1371 | + } elseif ($token['type'] === HTML5::EOF) { |
|
| 1372 | 1372 | /* Generate implied end tags. */ |
| 1373 | 1373 | $this->generateImpliedEndTags(); |
| 1374 | 1374 | |
| 1375 | 1375 | /* Anything else. */ |
| 1376 | 1376 | } else { |
| 1377 | 1377 | /* Depends on the insertion mode: */ |
| 1378 | - switch($this->mode) { |
|
| 1378 | + switch ($this->mode) { |
|
| 1379 | 1379 | case self::BEFOR_HEAD: return $this->beforeHead($token); break; |
| 1380 | 1380 | case self::IN_HEAD: return $this->inHead($token); break; |
| 1381 | 1381 | case self::AFTER_HEAD: return $this->afterHead($token); break; |
@@ -1401,19 +1401,19 @@ discard block |
||
| 1401 | 1401 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 1402 | 1402 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1403 | 1403 | or U+0020 SPACE */ |
| 1404 | - if($token['type'] === HTML5::CHARACTR && |
|
| 1404 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 1405 | 1405 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 1406 | 1406 | /* Append the character to the current node. */ |
| 1407 | 1407 | $this->insertText($token['data']); |
| 1408 | 1408 | |
| 1409 | 1409 | /* A comment token */ |
| 1410 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1410 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 1411 | 1411 | /* Append a Comment node to the current node with the data attribute |
| 1412 | 1412 | set to the data given in the comment token. */ |
| 1413 | 1413 | $this->insertComment($token['data']); |
| 1414 | 1414 | |
| 1415 | 1415 | /* A start tag token with the tag name "head" */ |
| 1416 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') { |
|
| 1416 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') { |
|
| 1417 | 1417 | /* Create an element for the token, append the new element to the |
| 1418 | 1418 | current node and push it onto the stack of open elements. */ |
| 1419 | 1419 | $element = $this->insertElement($token); |
@@ -1429,7 +1429,7 @@ discard block |
||
| 1429 | 1429 | Or a character token that is not one of U+0009 CHARACTER TABULATION, |
| 1430 | 1430 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1431 | 1431 | or U+0020 SPACE. Or any other start tag token */ |
| 1432 | - } elseif($token['type'] === HTML5::STARTTAG || |
|
| 1432 | + } elseif ($token['type'] === HTML5::STARTTAG || |
|
| 1433 | 1433 | ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') || |
| 1434 | 1434 | ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/', |
| 1435 | 1435 | $token['data']))) { |
@@ -1444,7 +1444,7 @@ discard block |
||
| 1444 | 1444 | return $this->inHead($token); |
| 1445 | 1445 | |
| 1446 | 1446 | /* Any other end tag */ |
| 1447 | - } elseif($token['type'] === HTML5::ENDTAG) { |
|
| 1447 | + } elseif ($token['type'] === HTML5::ENDTAG) { |
|
| 1448 | 1448 | /* Parse error. Ignore the token. */ |
| 1449 | 1449 | } |
| 1450 | 1450 | } |
@@ -1459,7 +1459,7 @@ discard block |
||
| 1459 | 1459 | THIS DIFFERS FROM THE SPEC: If the current node is either a title, style |
| 1460 | 1460 | or script element, append the character to the current node regardless |
| 1461 | 1461 | of its content. */ |
| 1462 | - if(($token['type'] === HTML5::CHARACTR && |
|
| 1462 | + if (($token['type'] === HTML5::CHARACTR && |
|
| 1463 | 1463 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || ( |
| 1464 | 1464 | $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName, |
| 1465 | 1465 | array('title', 'style', 'script')))) { |
@@ -1467,22 +1467,22 @@ discard block |
||
| 1467 | 1467 | $this->insertText($token['data']); |
| 1468 | 1468 | |
| 1469 | 1469 | /* A comment token */ |
| 1470 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1470 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 1471 | 1471 | /* Append a Comment node to the current node with the data attribute |
| 1472 | 1472 | set to the data given in the comment token. */ |
| 1473 | 1473 | $this->insertComment($token['data']); |
| 1474 | 1474 | |
| 1475 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 1475 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 1476 | 1476 | in_array($token['name'], array('title', 'style', 'script'))) { |
| 1477 | 1477 | array_pop($this->stack); |
| 1478 | 1478 | return HTML5::PCDATA; |
| 1479 | 1479 | |
| 1480 | 1480 | /* A start tag with the tag name "title" */ |
| 1481 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') { |
|
| 1481 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') { |
|
| 1482 | 1482 | /* Create an element for the token and append the new element to the |
| 1483 | 1483 | node pointed to by the head element pointer, or, if that is null |
| 1484 | 1484 | (innerHTML case), to the current node. */ |
| 1485 | - if($this->head_pointer !== null) { |
|
| 1485 | + if ($this->head_pointer !== null) { |
|
| 1486 | 1486 | $element = $this->insertElement($token, false); |
| 1487 | 1487 | $this->head_pointer->appendChild($element); |
| 1488 | 1488 | |
@@ -1494,11 +1494,11 @@ discard block |
||
| 1494 | 1494 | return HTML5::RCDATA; |
| 1495 | 1495 | |
| 1496 | 1496 | /* A start tag with the tag name "style" */ |
| 1497 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') { |
|
| 1497 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') { |
|
| 1498 | 1498 | /* Create an element for the token and append the new element to the |
| 1499 | 1499 | node pointed to by the head element pointer, or, if that is null |
| 1500 | 1500 | (innerHTML case), to the current node. */ |
| 1501 | - if($this->head_pointer !== null) { |
|
| 1501 | + if ($this->head_pointer !== null) { |
|
| 1502 | 1502 | $element = $this->insertElement($token, false); |
| 1503 | 1503 | $this->head_pointer->appendChild($element); |
| 1504 | 1504 | |
@@ -1510,7 +1510,7 @@ discard block |
||
| 1510 | 1510 | return HTML5::CDATA; |
| 1511 | 1511 | |
| 1512 | 1512 | /* A start tag with the tag name "script" */ |
| 1513 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { |
|
| 1513 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { |
|
| 1514 | 1514 | /* Create an element for the token. */ |
| 1515 | 1515 | $element = $this->insertElement($token, false); |
| 1516 | 1516 | $this->head_pointer->appendChild($element); |
@@ -1519,12 +1519,12 @@ discard block |
||
| 1519 | 1519 | return HTML5::CDATA; |
| 1520 | 1520 | |
| 1521 | 1521 | /* A start tag with the tag name "base", "link", or "meta" */ |
| 1522 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1522 | + } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1523 | 1523 | array('base', 'link', 'meta'))) { |
| 1524 | 1524 | /* Create an element for the token and append the new element to the |
| 1525 | 1525 | node pointed to by the head element pointer, or, if that is null |
| 1526 | 1526 | (innerHTML case), to the current node. */ |
| 1527 | - if($this->head_pointer !== null) { |
|
| 1527 | + if ($this->head_pointer !== null) { |
|
| 1528 | 1528 | $element = $this->insertElement($token, false); |
| 1529 | 1529 | $this->head_pointer->appendChild($element); |
| 1530 | 1530 | array_pop($this->stack); |
@@ -1534,10 +1534,10 @@ discard block |
||
| 1534 | 1534 | } |
| 1535 | 1535 | |
| 1536 | 1536 | /* An end tag with the tag name "head" */ |
| 1537 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { |
|
| 1537 | + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { |
|
| 1538 | 1538 | /* If the current node is a head element, pop the current node off |
| 1539 | 1539 | the stack of open elements. */ |
| 1540 | - if($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1540 | + if ($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1541 | 1541 | array_pop($this->stack); |
| 1542 | 1542 | |
| 1543 | 1543 | /* Otherwise, this is a parse error. */ |
@@ -1549,7 +1549,7 @@ discard block |
||
| 1549 | 1549 | $this->mode = self::AFTER_HEAD; |
| 1550 | 1550 | |
| 1551 | 1551 | /* A start tag with the tag name "head" or an end tag except "html". */ |
| 1552 | - } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || |
|
| 1552 | + } elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || |
|
| 1553 | 1553 | ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) { |
| 1554 | 1554 | // Parse error. Ignore the token. |
| 1555 | 1555 | |
@@ -1557,7 +1557,7 @@ discard block |
||
| 1557 | 1557 | } else { |
| 1558 | 1558 | /* If the current node is a head element, act as if an end tag |
| 1559 | 1559 | token with the tag name "head" had been seen. */ |
| 1560 | - if($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1560 | + if ($this->head_pointer->isSameNode(end($this->stack))) { |
|
| 1561 | 1561 | $this->inHead(array( |
| 1562 | 1562 | 'name' => 'head', |
| 1563 | 1563 | 'type' => HTML5::ENDTAG |
@@ -1579,19 +1579,19 @@ discard block |
||
| 1579 | 1579 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 1580 | 1580 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 1581 | 1581 | or U+0020 SPACE */ |
| 1582 | - if($token['type'] === HTML5::CHARACTR && |
|
| 1582 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 1583 | 1583 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 1584 | 1584 | /* Append the character to the current node. */ |
| 1585 | 1585 | $this->insertText($token['data']); |
| 1586 | 1586 | |
| 1587 | 1587 | /* A comment token */ |
| 1588 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 1588 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 1589 | 1589 | /* Append a Comment node to the current node with the data attribute |
| 1590 | 1590 | set to the data given in the comment token. */ |
| 1591 | 1591 | $this->insertComment($token['data']); |
| 1592 | 1592 | |
| 1593 | 1593 | /* A start tag token with the tag name "body" */ |
| 1594 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') { |
|
| 1594 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') { |
|
| 1595 | 1595 | /* Insert a body element for the token. */ |
| 1596 | 1596 | $this->insertElement($token); |
| 1597 | 1597 | |
@@ -1599,7 +1599,7 @@ discard block |
||
| 1599 | 1599 | $this->mode = self::IN_BODY; |
| 1600 | 1600 | |
| 1601 | 1601 | /* A start tag token with the tag name "frameset" */ |
| 1602 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') { |
|
| 1602 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') { |
|
| 1603 | 1603 | /* Insert a frameset element for the token. */ |
| 1604 | 1604 | $this->insertElement($token); |
| 1605 | 1605 | |
@@ -1608,7 +1608,7 @@ discard block |
||
| 1608 | 1608 | |
| 1609 | 1609 | /* A start tag token whose tag name is one of: "base", "link", "meta", |
| 1610 | 1610 | "script", "style", "title" */ |
| 1611 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1611 | + } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 1612 | 1612 | array('base', 'link', 'meta', 'script', 'style', 'title'))) { |
| 1613 | 1613 | /* Parse error. Switch the insertion mode back to "in head" and |
| 1614 | 1614 | reprocess the token. */ |
@@ -1632,7 +1632,7 @@ discard block |
||
| 1632 | 1632 | private function inBody($token) { |
| 1633 | 1633 | /* Handle the token as follows: */ |
| 1634 | 1634 | |
| 1635 | - switch($token['type']) { |
|
| 1635 | + switch ($token['type']) { |
|
| 1636 | 1636 | /* A character token */ |
| 1637 | 1637 | case HTML5::CHARACTR: |
| 1638 | 1638 | /* Reconstruct the active formatting elements, if any. */ |
@@ -1650,7 +1650,7 @@ discard block |
||
| 1650 | 1650 | break; |
| 1651 | 1651 | |
| 1652 | 1652 | case HTML5::STARTTAG: |
| 1653 | - switch($token['name']) { |
|
| 1653 | + switch ($token['name']) { |
|
| 1654 | 1654 | /* A start tag token whose tag name is one of: "script", |
| 1655 | 1655 | "style" */ |
| 1656 | 1656 | case 'script': case 'style': |
@@ -1673,7 +1673,7 @@ discard block |
||
| 1673 | 1673 | elements is not a body element, or, if the stack of open |
| 1674 | 1674 | elements has only one node on it, then ignore the token. |
| 1675 | 1675 | (innerHTML case) */ |
| 1676 | - if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') { |
|
| 1676 | + if (count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') { |
|
| 1677 | 1677 | // Ignore |
| 1678 | 1678 | |
| 1679 | 1679 | /* Otherwise, for each attribute on the token, check to see |
@@ -1682,8 +1682,8 @@ discard block |
||
| 1682 | 1682 | add the attribute and its corresponding value to that |
| 1683 | 1683 | element. */ |
| 1684 | 1684 | } else { |
| 1685 | - foreach($token['attr'] as $attr) { |
|
| 1686 | - if(!$this->stack[1]->hasAttribute($attr['name'])) { |
|
| 1685 | + foreach ($token['attr'] as $attr) { |
|
| 1686 | + if (!$this->stack[1]->hasAttribute($attr['name'])) { |
|
| 1687 | 1687 | $this->stack[1]->setAttribute($attr['name'], $attr['value']); |
| 1688 | 1688 | } |
| 1689 | 1689 | } |
@@ -1699,7 +1699,7 @@ discard block |
||
| 1699 | 1699 | /* If the stack of open elements has a p element in scope, |
| 1700 | 1700 | then act as if an end tag with the tag name p had been |
| 1701 | 1701 | seen. */ |
| 1702 | - if($this->elementInScope('p')) { |
|
| 1702 | + if ($this->elementInScope('p')) { |
|
| 1703 | 1703 | $this->emitToken(array( |
| 1704 | 1704 | 'name' => 'p', |
| 1705 | 1705 | 'type' => HTML5::ENDTAG |
@@ -1714,7 +1714,7 @@ discard block |
||
| 1714 | 1714 | case 'form': |
| 1715 | 1715 | /* If the form element pointer is not null, ignore the |
| 1716 | 1716 | token with a parse error. */ |
| 1717 | - if($this->form_pointer !== null) { |
|
| 1717 | + if ($this->form_pointer !== null) { |
|
| 1718 | 1718 | // Ignore. |
| 1719 | 1719 | |
| 1720 | 1720 | /* Otherwise: */ |
@@ -1722,7 +1722,7 @@ discard block |
||
| 1722 | 1722 | /* If the stack of open elements has a p element in |
| 1723 | 1723 | scope, then act as if an end tag with the tag name p |
| 1724 | 1724 | had been seen. */ |
| 1725 | - if($this->elementInScope('p')) { |
|
| 1725 | + if ($this->elementInScope('p')) { |
|
| 1726 | 1726 | $this->emitToken(array( |
| 1727 | 1727 | 'name' => 'p', |
| 1728 | 1728 | 'type' => HTML5::ENDTAG |
@@ -1741,7 +1741,7 @@ discard block |
||
| 1741 | 1741 | /* If the stack of open elements has a p element in scope, |
| 1742 | 1742 | then act as if an end tag with the tag name p had been |
| 1743 | 1743 | seen. */ |
| 1744 | - if($this->elementInScope('p')) { |
|
| 1744 | + if ($this->elementInScope('p')) { |
|
| 1745 | 1745 | $this->emitToken(array( |
| 1746 | 1746 | 'name' => 'p', |
| 1747 | 1747 | 'type' => HTML5::ENDTAG |
@@ -1750,7 +1750,7 @@ discard block |
||
| 1750 | 1750 | |
| 1751 | 1751 | $stack_length = count($this->stack) - 1; |
| 1752 | 1752 | |
| 1753 | - for($n = $stack_length; 0 <= $n; $n--) { |
|
| 1753 | + for ($n = $stack_length; 0 <= $n; $n--) { |
|
| 1754 | 1754 | /* 1. Initialise node to be the current node (the |
| 1755 | 1755 | bottommost node of the stack). */ |
| 1756 | 1756 | $stop = false; |
@@ -1760,9 +1760,9 @@ discard block |
||
| 1760 | 1760 | /* 2. If node is an li, dd or dt element, then pop all |
| 1761 | 1761 | the nodes from the current node up to node, including |
| 1762 | 1762 | node, then stop this algorithm. */ |
| 1763 | - if($token['name'] === $node->tagName || ($token['name'] !== 'li' |
|
| 1763 | + if ($token['name'] === $node->tagName || ($token['name'] !== 'li' |
|
| 1764 | 1764 | && ($node->tagName === 'dd' || $node->tagName === 'dt'))) { |
| 1765 | - for($x = $stack_length; $x >= $n ; $x--) { |
|
| 1765 | + for ($x = $stack_length; $x >= $n; $x--) { |
|
| 1766 | 1766 | array_pop($this->stack); |
| 1767 | 1767 | } |
| 1768 | 1768 | |
@@ -1772,7 +1772,7 @@ discard block |
||
| 1772 | 1772 | /* 3. If node is not in the formatting category, and is |
| 1773 | 1773 | not in the phrasing category, and is not an address or |
| 1774 | 1774 | div element, then stop this algorithm. */ |
| 1775 | - if($cat !== self::FORMATTING && $cat !== self::PHRASING && |
|
| 1775 | + if ($cat !== self::FORMATTING && $cat !== self::PHRASING && |
|
| 1776 | 1776 | $node->tagName !== 'address' && $node->tagName !== 'div') { |
| 1777 | 1777 | break; |
| 1778 | 1778 | } |
@@ -1788,7 +1788,7 @@ discard block |
||
| 1788 | 1788 | /* If the stack of open elements has a p element in scope, |
| 1789 | 1789 | then act as if an end tag with the tag name p had been |
| 1790 | 1790 | seen. */ |
| 1791 | - if($this->elementInScope('p')) { |
|
| 1791 | + if ($this->elementInScope('p')) { |
|
| 1792 | 1792 | $this->emitToken(array( |
| 1793 | 1793 | 'name' => 'p', |
| 1794 | 1794 | 'type' => HTML5::ENDTAG |
@@ -1806,7 +1806,7 @@ discard block |
||
| 1806 | 1806 | case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6': |
| 1807 | 1807 | /* If the stack of open elements has a p element in scope, |
| 1808 | 1808 | then act as if an end tag with the tag name p had been seen. */ |
| 1809 | - if($this->elementInScope('p')) { |
|
| 1809 | + if ($this->elementInScope('p')) { |
|
| 1810 | 1810 | $this->emitToken(array( |
| 1811 | 1811 | 'name' => 'p', |
| 1812 | 1812 | 'type' => HTML5::ENDTAG |
@@ -1818,7 +1818,7 @@ discard block |
||
| 1818 | 1818 | this is a parse error; pop elements from the stack until an |
| 1819 | 1819 | element with one of those tag names has been popped from the |
| 1820 | 1820 | stack. */ |
| 1821 | - while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { |
|
| 1821 | + while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { |
|
| 1822 | 1822 | array_pop($this->stack); |
| 1823 | 1823 | } |
| 1824 | 1824 | |
@@ -1839,11 +1839,11 @@ discard block |
||
| 1839 | 1839 | might not have if the element is not in table scope). */ |
| 1840 | 1840 | $leng = count($this->a_formatting); |
| 1841 | 1841 | |
| 1842 | - for($n = $leng - 1; $n >= 0; $n--) { |
|
| 1843 | - if($this->a_formatting[$n] === self::MARKER) { |
|
| 1842 | + for ($n = $leng - 1; $n >= 0; $n--) { |
|
| 1843 | + if ($this->a_formatting[$n] === self::MARKER) { |
|
| 1844 | 1844 | break; |
| 1845 | 1845 | |
| 1846 | - } elseif($this->a_formatting[$n]->nodeName === 'a') { |
|
| 1846 | + } elseif ($this->a_formatting[$n]->nodeName === 'a') { |
|
| 1847 | 1847 | $this->emitToken(array( |
| 1848 | 1848 | 'name' => 'a', |
| 1849 | 1849 | 'type' => HTML5::ENDTAG |
@@ -1885,7 +1885,7 @@ discard block |
||
| 1885 | 1885 | then this is a parse error; act as if an end tag with the tag |
| 1886 | 1886 | name "button" had been seen, then reprocess the token. (We don't |
| 1887 | 1887 | do that. Unnecessary.) */ |
| 1888 | - if($this->elementInScope('button')) { |
|
| 1888 | + if ($this->elementInScope('button')) { |
|
| 1889 | 1889 | $this->inBody(array( |
| 1890 | 1890 | 'name' => 'button', |
| 1891 | 1891 | 'type' => HTML5::ENDTAG |
@@ -1932,7 +1932,7 @@ discard block |
||
| 1932 | 1932 | case 'table': |
| 1933 | 1933 | /* If the stack of open elements has a p element in scope, |
| 1934 | 1934 | then act as if an end tag with the tag name p had been seen. */ |
| 1935 | - if($this->elementInScope('p')) { |
|
| 1935 | + if ($this->elementInScope('p')) { |
|
| 1936 | 1936 | $this->emitToken(array( |
| 1937 | 1937 | 'name' => 'p', |
| 1938 | 1938 | 'type' => HTML5::ENDTAG |
@@ -1965,7 +1965,7 @@ discard block |
||
| 1965 | 1965 | case 'hr': |
| 1966 | 1966 | /* If the stack of open elements has a p element in scope, |
| 1967 | 1967 | then act as if an end tag with the tag name p had been seen. */ |
| 1968 | - if($this->elementInScope('p')) { |
|
| 1968 | + if ($this->elementInScope('p')) { |
|
| 1969 | 1969 | $this->emitToken(array( |
| 1970 | 1970 | 'name' => 'p', |
| 1971 | 1971 | 'type' => HTML5::ENDTAG |
@@ -2013,7 +2013,7 @@ discard block |
||
| 2013 | 2013 | |
| 2014 | 2014 | /* If the form element pointer is not null, |
| 2015 | 2015 | then ignore the token. */ |
| 2016 | - if($this->form_pointer === null) { |
|
| 2016 | + if ($this->form_pointer === null) { |
|
| 2017 | 2017 | /* Act as if a start tag token with the tag name "form" had |
| 2018 | 2018 | been seen. */ |
| 2019 | 2019 | $this->inBody(array( |
@@ -2158,18 +2158,18 @@ discard block |
||
| 2158 | 2158 | break; |
| 2159 | 2159 | |
| 2160 | 2160 | case HTML5::ENDTAG: |
| 2161 | - switch($token['name']) { |
|
| 2161 | + switch ($token['name']) { |
|
| 2162 | 2162 | /* An end tag with the tag name "body" */ |
| 2163 | 2163 | case 'body': |
| 2164 | 2164 | /* If the second element in the stack of open elements is |
| 2165 | 2165 | not a body element, this is a parse error. Ignore the token. |
| 2166 | 2166 | (innerHTML case) */ |
| 2167 | - if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') { |
|
| 2167 | + if (count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') { |
|
| 2168 | 2168 | // Ignore. |
| 2169 | 2169 | |
| 2170 | 2170 | /* If the current node is not the body element, then this |
| 2171 | 2171 | is a parse error. */ |
| 2172 | - } elseif(end($this->stack)->nodeName !== 'body') { |
|
| 2172 | + } elseif (end($this->stack)->nodeName !== 'body') { |
|
| 2173 | 2173 | // Parse error. |
| 2174 | 2174 | } |
| 2175 | 2175 | |
@@ -2199,7 +2199,7 @@ discard block |
||
| 2199 | 2199 | /* If the stack of open elements has an element in scope |
| 2200 | 2200 | with the same tag name as that of the token, then generate |
| 2201 | 2201 | implied end tags. */ |
| 2202 | - if($this->elementInScope($token['name'])) { |
|
| 2202 | + if ($this->elementInScope($token['name'])) { |
|
| 2203 | 2203 | $this->generateImpliedEndTags(); |
| 2204 | 2204 | |
| 2205 | 2205 | /* Now, if the current node is not an element with |
@@ -2211,8 +2211,8 @@ discard block |
||
| 2211 | 2211 | scope with the same tag name as that of the token, |
| 2212 | 2212 | then pop elements from this stack until an element |
| 2213 | 2213 | with that tag name has been popped from the stack. */ |
| 2214 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2215 | - if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2214 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2215 | + if ($this->stack[$n]->nodeName === $token['name']) { |
|
| 2216 | 2216 | $n = -1; |
| 2217 | 2217 | } |
| 2218 | 2218 | |
@@ -2226,12 +2226,12 @@ discard block |
||
| 2226 | 2226 | /* If the stack of open elements has an element in scope |
| 2227 | 2227 | with the same tag name as that of the token, then generate |
| 2228 | 2228 | implied end tags. */ |
| 2229 | - if($this->elementInScope($token['name'])) { |
|
| 2229 | + if ($this->elementInScope($token['name'])) { |
|
| 2230 | 2230 | $this->generateImpliedEndTags(); |
| 2231 | 2231 | |
| 2232 | 2232 | } |
| 2233 | 2233 | |
| 2234 | - if(end($this->stack)->nodeName !== $token['name']) { |
|
| 2234 | + if (end($this->stack)->nodeName !== $token['name']) { |
|
| 2235 | 2235 | /* Now, if the current node is not an element with the |
| 2236 | 2236 | same tag name as that of the token, then this is a parse |
| 2237 | 2237 | error. */ |
@@ -2252,7 +2252,7 @@ discard block |
||
| 2252 | 2252 | case 'p': |
| 2253 | 2253 | /* If the stack of open elements has a p element in scope, |
| 2254 | 2254 | then generate implied end tags, except for p elements. */ |
| 2255 | - if($this->elementInScope('p')) { |
|
| 2255 | + if ($this->elementInScope('p')) { |
|
| 2256 | 2256 | $this->generateImpliedEndTags(array('p')); |
| 2257 | 2257 | |
| 2258 | 2258 | /* If the current node is not a p element, then this is |
@@ -2262,8 +2262,8 @@ discard block |
||
| 2262 | 2262 | /* If the stack of open elements has a p element in |
| 2263 | 2263 | scope, then pop elements from this stack until the stack |
| 2264 | 2264 | no longer has a p element in scope. */ |
| 2265 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2266 | - if($this->elementInScope('p')) { |
|
| 2265 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2266 | + if ($this->elementInScope('p')) { |
|
| 2267 | 2267 | array_pop($this->stack); |
| 2268 | 2268 | |
| 2269 | 2269 | } else { |
@@ -2279,7 +2279,7 @@ discard block |
||
| 2279 | 2279 | whose tag name matches the tag name of the token, then |
| 2280 | 2280 | generate implied end tags, except for elements with the |
| 2281 | 2281 | same tag name as the token. */ |
| 2282 | - if($this->elementInScope($token['name'])) { |
|
| 2282 | + if ($this->elementInScope($token['name'])) { |
|
| 2283 | 2283 | $this->generateImpliedEndTags(array($token['name'])); |
| 2284 | 2284 | |
| 2285 | 2285 | /* If the current node is not an element with the same |
@@ -2290,8 +2290,8 @@ discard block |
||
| 2290 | 2290 | whose tag name matches the tag name of the token, then |
| 2291 | 2291 | pop elements from this stack until an element with that |
| 2292 | 2292 | tag name has been popped from the stack. */ |
| 2293 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2294 | - if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2293 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2294 | + if ($this->stack[$n]->nodeName === $token['name']) { |
|
| 2295 | 2295 | $n = -1; |
| 2296 | 2296 | } |
| 2297 | 2297 | |
@@ -2308,7 +2308,7 @@ discard block |
||
| 2308 | 2308 | /* If the stack of open elements has in scope an element whose |
| 2309 | 2309 | tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then |
| 2310 | 2310 | generate implied end tags. */ |
| 2311 | - if($this->elementInScope($elements)) { |
|
| 2311 | + if ($this->elementInScope($elements)) { |
|
| 2312 | 2312 | $this->generateImpliedEndTags(); |
| 2313 | 2313 | |
| 2314 | 2314 | /* Now, if the current node is not an element with the same |
@@ -2319,7 +2319,7 @@ discard block |
||
| 2319 | 2319 | whose tag name is one of "h1", "h2", "h3", "h4", "h5", or |
| 2320 | 2320 | "h6", then pop elements from the stack until an element |
| 2321 | 2321 | with one of those tag names has been popped from the stack. */ |
| 2322 | - while($this->elementInScope($elements)) { |
|
| 2322 | + while ($this->elementInScope($elements)) { |
|
| 2323 | 2323 | array_pop($this->stack); |
| 2324 | 2324 | } |
| 2325 | 2325 | } |
@@ -2337,12 +2337,12 @@ discard block |
||
| 2337 | 2337 | otherwise, and |
| 2338 | 2338 | * has the same tag name as the token. |
| 2339 | 2339 | */ |
| 2340 | - while(true) { |
|
| 2341 | - for($a = count($this->a_formatting) - 1; $a >= 0; $a--) { |
|
| 2342 | - if($this->a_formatting[$a] === self::MARKER) { |
|
| 2340 | + while (true) { |
|
| 2341 | + for ($a = count($this->a_formatting) - 1; $a >= 0; $a--) { |
|
| 2342 | + if ($this->a_formatting[$a] === self::MARKER) { |
|
| 2343 | 2343 | break; |
| 2344 | 2344 | |
| 2345 | - } elseif($this->a_formatting[$a]->tagName === $token['name']) { |
|
| 2345 | + } elseif ($this->a_formatting[$a]->tagName === $token['name']) { |
|
| 2346 | 2346 | $formatting_element = $this->a_formatting[$a]; |
| 2347 | 2347 | $in_stack = in_array($formatting_element, $this->stack, true); |
| 2348 | 2348 | $fe_af_pos = $a; |
@@ -2354,7 +2354,7 @@ discard block |
||
| 2354 | 2354 | also in the stack of open elements but the element |
| 2355 | 2355 | is not in scope, then this is a parse error. Abort |
| 2356 | 2356 | these steps. The token is ignored. */ |
| 2357 | - if(!isset($formatting_element) || ($in_stack && |
|
| 2357 | + if (!isset($formatting_element) || ($in_stack && |
|
| 2358 | 2358 | !$this->elementInScope($token['name']))) { |
| 2359 | 2359 | break; |
| 2360 | 2360 | |
@@ -2362,7 +2362,7 @@ discard block |
||
| 2362 | 2362 | is not in the stack of open elements, then this is a |
| 2363 | 2363 | parse error; remove the element from the list, and |
| 2364 | 2364 | abort these steps. */ |
| 2365 | - } elseif(isset($formatting_element) && !$in_stack) { |
|
| 2365 | + } elseif (isset($formatting_element) && !$in_stack) { |
|
| 2366 | 2366 | unset($this->a_formatting[$fe_af_pos]); |
| 2367 | 2367 | $this->a_formatting = array_merge($this->a_formatting); |
| 2368 | 2368 | break; |
@@ -2376,10 +2376,10 @@ discard block |
||
| 2376 | 2376 | $fe_s_pos = array_search($formatting_element, $this->stack, true); |
| 2377 | 2377 | $length = count($this->stack); |
| 2378 | 2378 | |
| 2379 | - for($s = $fe_s_pos + 1; $s < $length; $s++) { |
|
| 2379 | + for ($s = $fe_s_pos + 1; $s < $length; $s++) { |
|
| 2380 | 2380 | $category = $this->getElementCategory($this->stack[$s]->nodeName); |
| 2381 | 2381 | |
| 2382 | - if($category !== self::PHRASING && $category !== self::FORMATTING) { |
|
| 2382 | + if ($category !== self::PHRASING && $category !== self::FORMATTING) { |
|
| 2383 | 2383 | $furthest_block = $this->stack[$s]; |
| 2384 | 2384 | } |
| 2385 | 2385 | } |
@@ -2390,8 +2390,8 @@ discard block |
||
| 2390 | 2390 | elements, from the current node up to the formatting |
| 2391 | 2391 | element, and remove the formatting element from the |
| 2392 | 2392 | list of active formatting elements. */ |
| 2393 | - if(!isset($furthest_block)) { |
|
| 2394 | - for($n = $length - 1; $n >= $fe_s_pos; $n--) { |
|
| 2393 | + if (!isset($furthest_block)) { |
|
| 2394 | + for ($n = $length - 1; $n >= $fe_s_pos; $n--) { |
|
| 2395 | 2395 | array_pop($this->stack); |
| 2396 | 2396 | } |
| 2397 | 2397 | |
@@ -2407,7 +2407,7 @@ discard block |
||
| 2407 | 2407 | |
| 2408 | 2408 | /* 5. If the furthest block has a parent node, then |
| 2409 | 2409 | remove the furthest block from its parent node. */ |
| 2410 | - if($furthest_block->parentNode !== null) { |
|
| 2410 | + if ($furthest_block->parentNode !== null) { |
|
| 2411 | 2411 | $furthest_block->parentNode->removeChild($furthest_block); |
| 2412 | 2412 | } |
| 2413 | 2413 | |
@@ -2422,8 +2422,8 @@ discard block |
||
| 2422 | 2422 | $node = $furthest_block; |
| 2423 | 2423 | $last_node = $furthest_block; |
| 2424 | 2424 | |
| 2425 | - while(true) { |
|
| 2426 | - for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) { |
|
| 2425 | + while (true) { |
|
| 2426 | + for ($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) { |
|
| 2427 | 2427 | /* 7.1 Let node be the element immediately |
| 2428 | 2428 | prior to node in the stack of open elements. */ |
| 2429 | 2429 | $node = $this->stack[$n]; |
@@ -2432,7 +2432,7 @@ discard block |
||
| 2432 | 2432 | formatting elements, then remove node from |
| 2433 | 2433 | the stack of open elements and then go back |
| 2434 | 2434 | to step 1. */ |
| 2435 | - if(!in_array($node, $this->a_formatting, true)) { |
|
| 2435 | + if (!in_array($node, $this->a_formatting, true)) { |
|
| 2436 | 2436 | unset($this->stack[$n]); |
| 2437 | 2437 | $this->stack = array_merge($this->stack); |
| 2438 | 2438 | |
@@ -2444,14 +2444,14 @@ discard block |
||
| 2444 | 2444 | /* 7.3 Otherwise, if node is the formatting |
| 2445 | 2445 | element, then go to the next step in the overall |
| 2446 | 2446 | algorithm. */ |
| 2447 | - if($node === $formatting_element) { |
|
| 2447 | + if ($node === $formatting_element) { |
|
| 2448 | 2448 | break; |
| 2449 | 2449 | |
| 2450 | 2450 | /* 7.4 Otherwise, if last node is the furthest |
| 2451 | 2451 | block, then move the aforementioned bookmark to |
| 2452 | 2452 | be immediately after the node in the list of |
| 2453 | 2453 | active formatting elements. */ |
| 2454 | - } elseif($last_node === $furthest_block) { |
|
| 2454 | + } elseif ($last_node === $furthest_block) { |
|
| 2455 | 2455 | $bookmark = array_search($node, $this->a_formatting, true) + 1; |
| 2456 | 2456 | } |
| 2457 | 2457 | |
@@ -2461,7 +2461,7 @@ discard block |
||
| 2461 | 2461 | with an entry for the clone, replace the entry |
| 2462 | 2462 | for node in the stack of open elements with an |
| 2463 | 2463 | entry for the clone, and let node be the clone. */ |
| 2464 | - if($node->hasChildNodes()) { |
|
| 2464 | + if ($node->hasChildNodes()) { |
|
| 2465 | 2465 | $clone = $node->cloneNode(); |
| 2466 | 2466 | $s_pos = array_search($node, $this->stack, true); |
| 2467 | 2467 | $a_pos = array_search($node, $this->a_formatting, true); |
@@ -2473,7 +2473,7 @@ discard block |
||
| 2473 | 2473 | |
| 2474 | 2474 | /* 7.6 Insert last node into node, first removing |
| 2475 | 2475 | it from its previous parent node if any. */ |
| 2476 | - if($last_node->parentNode !== null) { |
|
| 2476 | + if ($last_node->parentNode !== null) { |
|
| 2477 | 2477 | $last_node->parentNode->removeChild($last_node); |
| 2478 | 2478 | } |
| 2479 | 2479 | |
@@ -2487,7 +2487,7 @@ discard block |
||
| 2487 | 2487 | the previous step into the common ancestor node, |
| 2488 | 2488 | first removing it from its previous parent node if |
| 2489 | 2489 | any. */ |
| 2490 | - if($last_node->parentNode !== null) { |
|
| 2490 | + if ($last_node->parentNode !== null) { |
|
| 2491 | 2491 | $last_node->parentNode->removeChild($last_node); |
| 2492 | 2492 | } |
| 2493 | 2493 | |
@@ -2500,7 +2500,7 @@ discard block |
||
| 2500 | 2500 | /* 10. Take all of the child nodes of the furthest |
| 2501 | 2501 | block and append them to the clone created in the |
| 2502 | 2502 | last step. */ |
| 2503 | - while($furthest_block->hasChildNodes()) { |
|
| 2503 | + while ($furthest_block->hasChildNodes()) { |
|
| 2504 | 2504 | $child = $furthest_block->firstChild; |
| 2505 | 2505 | $furthest_block->removeChild($child); |
| 2506 | 2506 | $clone->appendChild($child); |
@@ -2545,7 +2545,7 @@ discard block |
||
| 2545 | 2545 | /* If the stack of open elements has an element in scope whose |
| 2546 | 2546 | tag name matches the tag name of the token, then generate implied |
| 2547 | 2547 | tags. */ |
| 2548 | - if($this->elementInScope($token['name'])) { |
|
| 2548 | + if ($this->elementInScope($token['name'])) { |
|
| 2549 | 2549 | $this->generateImpliedEndTags(); |
| 2550 | 2550 | |
| 2551 | 2551 | /* Now, if the current node is not an element with the same |
@@ -2557,8 +2557,8 @@ discard block |
||
| 2557 | 2557 | elements from the stack until that element has been popped from |
| 2558 | 2558 | the stack, and clear the list of active formatting elements up |
| 2559 | 2559 | to the last marker. */ |
| 2560 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2561 | - if($this->stack[$n]->nodeName === $token['name']) { |
|
| 2560 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2561 | + if ($this->stack[$n]->nodeName === $token['name']) { |
|
| 2562 | 2562 | $n = -1; |
| 2563 | 2563 | } |
| 2564 | 2564 | |
@@ -2567,7 +2567,7 @@ discard block |
||
| 2567 | 2567 | |
| 2568 | 2568 | $marker = end(array_keys($this->a_formatting, self::MARKER, true)); |
| 2569 | 2569 | |
| 2570 | - for($n = count($this->a_formatting) - 1; $n > $marker; $n--) { |
|
| 2570 | + for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) { |
|
| 2571 | 2571 | array_pop($this->a_formatting); |
| 2572 | 2572 | } |
| 2573 | 2573 | } |
@@ -2587,14 +2587,14 @@ discard block |
||
| 2587 | 2587 | |
| 2588 | 2588 | /* An end tag token not covered by the previous entries */ |
| 2589 | 2589 | default: |
| 2590 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2590 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2591 | 2591 | /* Initialise node to be the current node (the bottommost |
| 2592 | 2592 | node of the stack). */ |
| 2593 | 2593 | $node = end($this->stack); |
| 2594 | 2594 | |
| 2595 | 2595 | /* If node has the same tag name as the end tag token, |
| 2596 | 2596 | then: */ |
| 2597 | - if($token['name'] === $node->nodeName) { |
|
| 2597 | + if ($token['name'] === $node->nodeName) { |
|
| 2598 | 2598 | /* Generate implied end tags. */ |
| 2599 | 2599 | $this->generateImpliedEndTags(); |
| 2600 | 2600 | |
@@ -2605,14 +2605,14 @@ discard block |
||
| 2605 | 2605 | |
| 2606 | 2606 | /* Pop all the nodes from the current node up to |
| 2607 | 2607 | node, including node, then stop this algorithm. */ |
| 2608 | - for($x = count($this->stack) - $n; $x >= $n; $x--) { |
|
| 2608 | + for ($x = count($this->stack) - $n; $x >= $n; $x--) { |
|
| 2609 | 2609 | array_pop($this->stack); |
| 2610 | 2610 | } |
| 2611 | 2611 | |
| 2612 | 2612 | } else { |
| 2613 | 2613 | $category = $this->getElementCategory($node); |
| 2614 | 2614 | |
| 2615 | - if($category !== self::SPECIAL && $category !== self::SCOPING) { |
|
| 2615 | + if ($category !== self::SPECIAL && $category !== self::SCOPING) { |
|
| 2616 | 2616 | /* Otherwise, if node is in neither the formatting |
| 2617 | 2617 | category nor the phrasing category, then this is a |
| 2618 | 2618 | parse error. Stop this algorithm. The end tag token |
@@ -2633,21 +2633,21 @@ discard block |
||
| 2633 | 2633 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 2634 | 2634 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 2635 | 2635 | or U+0020 SPACE */ |
| 2636 | - if($token['type'] === HTML5::CHARACTR && |
|
| 2636 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 2637 | 2637 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 2638 | 2638 | /* Append the character to the current node. */ |
| 2639 | 2639 | $text = $this->dom->createTextNode($token['data']); |
| 2640 | 2640 | end($this->stack)->appendChild($text); |
| 2641 | 2641 | |
| 2642 | 2642 | /* A comment token */ |
| 2643 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 2643 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 2644 | 2644 | /* Append a Comment node to the current node with the data |
| 2645 | 2645 | attribute set to the data given in the comment token. */ |
| 2646 | 2646 | $comment = $this->dom->createComment($token['data']); |
| 2647 | 2647 | end($this->stack)->appendChild($comment); |
| 2648 | 2648 | |
| 2649 | 2649 | /* A start tag whose tag name is "caption" */ |
| 2650 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2650 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 2651 | 2651 | $token['name'] === 'caption') { |
| 2652 | 2652 | /* Clear the stack back to a table context. */ |
| 2653 | 2653 | $this->clearStackToTableContext($clear); |
@@ -2662,7 +2662,7 @@ discard block |
||
| 2662 | 2662 | $this->mode = self::IN_CAPTION; |
| 2663 | 2663 | |
| 2664 | 2664 | /* A start tag whose tag name is "colgroup" */ |
| 2665 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2665 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 2666 | 2666 | $token['name'] === 'colgroup') { |
| 2667 | 2667 | /* Clear the stack back to a table context. */ |
| 2668 | 2668 | $this->clearStackToTableContext($clear); |
@@ -2673,7 +2673,7 @@ discard block |
||
| 2673 | 2673 | $this->mode = self::IN_CGROUP; |
| 2674 | 2674 | |
| 2675 | 2675 | /* A start tag whose tag name is "col" */ |
| 2676 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2676 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 2677 | 2677 | $token['name'] === 'col') { |
| 2678 | 2678 | $this->inTable(array( |
| 2679 | 2679 | 'name' => 'colgroup', |
@@ -2684,7 +2684,7 @@ discard block |
||
| 2684 | 2684 | $this->inColumnGroup($token); |
| 2685 | 2685 | |
| 2686 | 2686 | /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
| 2687 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2687 | + } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2688 | 2688 | array('tbody', 'tfoot', 'thead'))) { |
| 2689 | 2689 | /* Clear the stack back to a table context. */ |
| 2690 | 2690 | $this->clearStackToTableContext($clear); |
@@ -2695,7 +2695,7 @@ discard block |
||
| 2695 | 2695 | $this->mode = self::IN_TBODY; |
| 2696 | 2696 | |
| 2697 | 2697 | /* A start tag whose tag name is one of: "td", "th", "tr" */ |
| 2698 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2698 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 2699 | 2699 | in_array($token['name'], array('td', 'th', 'tr'))) { |
| 2700 | 2700 | /* Act as if a start tag token with the tag name "tbody" had been |
| 2701 | 2701 | seen, then reprocess the current token. */ |
@@ -2708,7 +2708,7 @@ discard block |
||
| 2708 | 2708 | return $this->inTableBody($token); |
| 2709 | 2709 | |
| 2710 | 2710 | /* A start tag whose tag name is "table" */ |
| 2711 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2711 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 2712 | 2712 | $token['name'] === 'table') { |
| 2713 | 2713 | /* Parse error. Act as if an end tag token with the tag name "table" |
| 2714 | 2714 | had been seen, then, if that token wasn't ignored, reprocess the |
@@ -2721,12 +2721,12 @@ discard block |
||
| 2721 | 2721 | return $this->mainPhase($token); |
| 2722 | 2722 | |
| 2723 | 2723 | /* An end tag whose tag name is "table" */ |
| 2724 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2724 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 2725 | 2725 | $token['name'] === 'table') { |
| 2726 | 2726 | /* If the stack of open elements does not have an element in table |
| 2727 | 2727 | scope with the same tag name as the token, this is a parse error. |
| 2728 | 2728 | Ignore the token. (innerHTML case) */ |
| 2729 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 2729 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 2730 | 2730 | return false; |
| 2731 | 2731 | |
| 2732 | 2732 | /* Otherwise: */ |
@@ -2740,11 +2740,11 @@ discard block |
||
| 2740 | 2740 | |
| 2741 | 2741 | /* Pop elements from this stack until a table element has been |
| 2742 | 2742 | popped from the stack. */ |
| 2743 | - while(true) { |
|
| 2743 | + while (true) { |
|
| 2744 | 2744 | $current = end($this->stack)->nodeName; |
| 2745 | 2745 | array_pop($this->stack); |
| 2746 | 2746 | |
| 2747 | - if($current === 'table') { |
|
| 2747 | + if ($current === 'table') { |
|
| 2748 | 2748 | break; |
| 2749 | 2749 | } |
| 2750 | 2750 | } |
@@ -2755,7 +2755,7 @@ discard block |
||
| 2755 | 2755 | |
| 2756 | 2756 | /* An end tag whose tag name is one of: "body", "caption", "col", |
| 2757 | 2757 | "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 2758 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2758 | + } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2759 | 2759 | array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td', |
| 2760 | 2760 | 'tfoot', 'th', 'thead', 'tr'))) { |
| 2761 | 2761 | // Parse error. Ignore the token. |
@@ -2768,7 +2768,7 @@ discard block |
||
| 2768 | 2768 | /* If the current node is a table, tbody, tfoot, thead, or tr |
| 2769 | 2769 | element, then, whenever a node would be inserted into the current |
| 2770 | 2770 | node, it must instead be inserted into the foster parent element. */ |
| 2771 | - if(in_array(end($this->stack)->nodeName, |
|
| 2771 | + if (in_array(end($this->stack)->nodeName, |
|
| 2772 | 2772 | array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { |
| 2773 | 2773 | /* The foster parent element is the parent element of the last |
| 2774 | 2774 | table element in the stack of open elements, if there is a |
@@ -2781,20 +2781,20 @@ discard block |
||
| 2781 | 2781 | its parent node is not an element, then the foster parent |
| 2782 | 2782 | element is the element before the last table element in the |
| 2783 | 2783 | stack of open elements. */ |
| 2784 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2785 | - if($this->stack[$n]->nodeName === 'table') { |
|
| 2784 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 2785 | + if ($this->stack[$n]->nodeName === 'table') { |
|
| 2786 | 2786 | $table = $this->stack[$n]; |
| 2787 | 2787 | break; |
| 2788 | 2788 | } |
| 2789 | 2789 | } |
| 2790 | 2790 | |
| 2791 | - if(isset($table) && $table->parentNode !== null) { |
|
| 2791 | + if (isset($table) && $table->parentNode !== null) { |
|
| 2792 | 2792 | $this->foster_parent = $table->parentNode; |
| 2793 | 2793 | |
| 2794 | - } elseif(!isset($table)) { |
|
| 2794 | + } elseif (!isset($table)) { |
|
| 2795 | 2795 | $this->foster_parent = $this->stack[0]; |
| 2796 | 2796 | |
| 2797 | - } elseif(isset($table) && ($table->parentNode === null || |
|
| 2797 | + } elseif (isset($table) && ($table->parentNode === null || |
|
| 2798 | 2798 | $table->parentNode->nodeType !== XML_ELEMENT_NODE)) { |
| 2799 | 2799 | $this->foster_parent = $this->stack[$n - 1]; |
| 2800 | 2800 | } |
@@ -2806,11 +2806,11 @@ discard block |
||
| 2806 | 2806 | |
| 2807 | 2807 | private function inCaption($token) { |
| 2808 | 2808 | /* An end tag whose tag name is "caption" */ |
| 2809 | - if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { |
|
| 2809 | + if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { |
|
| 2810 | 2810 | /* If the stack of open elements does not have an element in table |
| 2811 | 2811 | scope with the same tag name as the token, this is a parse error. |
| 2812 | 2812 | Ignore the token. (innerHTML case) */ |
| 2813 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 2813 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 2814 | 2814 | // Ignore |
| 2815 | 2815 | |
| 2816 | 2816 | /* Otherwise: */ |
@@ -2824,11 +2824,11 @@ discard block |
||
| 2824 | 2824 | |
| 2825 | 2825 | /* Pop elements from this stack until a caption element has |
| 2826 | 2826 | been popped from the stack. */ |
| 2827 | - while(true) { |
|
| 2827 | + while (true) { |
|
| 2828 | 2828 | $node = end($this->stack)->nodeName; |
| 2829 | 2829 | array_pop($this->stack); |
| 2830 | 2830 | |
| 2831 | - if($node === 'caption') { |
|
| 2831 | + if ($node === 'caption') { |
|
| 2832 | 2832 | break; |
| 2833 | 2833 | } |
| 2834 | 2834 | } |
@@ -2844,7 +2844,7 @@ discard block |
||
| 2844 | 2844 | /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
| 2845 | 2845 | "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag |
| 2846 | 2846 | name is "table" */ |
| 2847 | - } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2847 | + } elseif (($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2848 | 2848 | array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
| 2849 | 2849 | 'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG && |
| 2850 | 2850 | $token['name'] === 'table')) { |
@@ -2860,7 +2860,7 @@ discard block |
||
| 2860 | 2860 | |
| 2861 | 2861 | /* An end tag whose tag name is one of: "body", "col", "colgroup", |
| 2862 | 2862 | "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 2863 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2863 | + } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 2864 | 2864 | array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th', |
| 2865 | 2865 | 'thead', 'tr'))) { |
| 2866 | 2866 | // Parse error. Ignore the token. |
@@ -2876,32 +2876,32 @@ discard block |
||
| 2876 | 2876 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 2877 | 2877 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 2878 | 2878 | or U+0020 SPACE */ |
| 2879 | - if($token['type'] === HTML5::CHARACTR && |
|
| 2879 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 2880 | 2880 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 2881 | 2881 | /* Append the character to the current node. */ |
| 2882 | 2882 | $text = $this->dom->createTextNode($token['data']); |
| 2883 | 2883 | end($this->stack)->appendChild($text); |
| 2884 | 2884 | |
| 2885 | 2885 | /* A comment token */ |
| 2886 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 2886 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 2887 | 2887 | /* Append a Comment node to the current node with the data |
| 2888 | 2888 | attribute set to the data given in the comment token. */ |
| 2889 | 2889 | $comment = $this->dom->createComment($token['data']); |
| 2890 | 2890 | end($this->stack)->appendChild($comment); |
| 2891 | 2891 | |
| 2892 | 2892 | /* A start tag whose tag name is "col" */ |
| 2893 | - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') { |
|
| 2893 | + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') { |
|
| 2894 | 2894 | /* Insert a col element for the token. Immediately pop the current |
| 2895 | 2895 | node off the stack of open elements. */ |
| 2896 | 2896 | $this->insertElement($token); |
| 2897 | 2897 | array_pop($this->stack); |
| 2898 | 2898 | |
| 2899 | 2899 | /* An end tag whose tag name is "colgroup" */ |
| 2900 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2900 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 2901 | 2901 | $token['name'] === 'colgroup') { |
| 2902 | 2902 | /* If the current node is the root html element, then this is a |
| 2903 | 2903 | parse error, ignore the token. (innerHTML case) */ |
| 2904 | - if(end($this->stack)->nodeName === 'html') { |
|
| 2904 | + if (end($this->stack)->nodeName === 'html') { |
|
| 2905 | 2905 | // Ignore |
| 2906 | 2906 | |
| 2907 | 2907 | /* Otherwise, pop the current node (which will be a colgroup |
@@ -2913,7 +2913,7 @@ discard block |
||
| 2913 | 2913 | } |
| 2914 | 2914 | |
| 2915 | 2915 | /* An end tag whose tag name is "col" */ |
| 2916 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { |
|
| 2916 | + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { |
|
| 2917 | 2917 | /* Parse error. Ignore the token. */ |
| 2918 | 2918 | |
| 2919 | 2919 | /* Anything else */ |
@@ -2933,7 +2933,7 @@ discard block |
||
| 2933 | 2933 | $clear = array('tbody', 'tfoot', 'thead', 'html'); |
| 2934 | 2934 | |
| 2935 | 2935 | /* A start tag whose tag name is "tr" */ |
| 2936 | - if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { |
|
| 2936 | + if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { |
|
| 2937 | 2937 | /* Clear the stack back to a table body context. */ |
| 2938 | 2938 | $this->clearStackToTableContext($clear); |
| 2939 | 2939 | |
@@ -2943,8 +2943,8 @@ discard block |
||
| 2943 | 2943 | $this->mode = self::IN_ROW; |
| 2944 | 2944 | |
| 2945 | 2945 | /* A start tag whose tag name is one of: "th", "td" */ |
| 2946 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 2947 | - ($token['name'] === 'th' || $token['name'] === 'td')) { |
|
| 2946 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 2947 | + ($token['name'] === 'th' || $token['name'] === 'td')) { |
|
| 2948 | 2948 | /* Parse error. Act as if a start tag with the tag name "tr" had |
| 2949 | 2949 | been seen, then reprocess the current token. */ |
| 2950 | 2950 | $this->inTableBody(array( |
@@ -2956,12 +2956,12 @@ discard block |
||
| 2956 | 2956 | return $this->inRow($token); |
| 2957 | 2957 | |
| 2958 | 2958 | /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
| 2959 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 2959 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 2960 | 2960 | in_array($token['name'], array('tbody', 'tfoot', 'thead'))) { |
| 2961 | 2961 | /* If the stack of open elements does not have an element in table |
| 2962 | 2962 | scope with the same tag name as the token, this is a parse error. |
| 2963 | 2963 | Ignore the token. */ |
| 2964 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 2964 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 2965 | 2965 | // Ignore |
| 2966 | 2966 | |
| 2967 | 2967 | /* Otherwise: */ |
@@ -2977,13 +2977,13 @@ discard block |
||
| 2977 | 2977 | |
| 2978 | 2978 | /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
| 2979 | 2979 | "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */ |
| 2980 | - } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2980 | + } elseif (($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 2981 | 2981 | array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) || |
| 2982 | 2982 | ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) { |
| 2983 | 2983 | /* If the stack of open elements does not have a tbody, thead, or |
| 2984 | 2984 | tfoot element in table scope, this is a parse error. Ignore the |
| 2985 | 2985 | token. (innerHTML case) */ |
| 2986 | - if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { |
|
| 2986 | + if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { |
|
| 2987 | 2987 | // Ignore. |
| 2988 | 2988 | |
| 2989 | 2989 | /* Otherwise: */ |
@@ -3004,7 +3004,7 @@ discard block |
||
| 3004 | 3004 | |
| 3005 | 3005 | /* An end tag whose tag name is one of: "body", "caption", "col", |
| 3006 | 3006 | "colgroup", "html", "td", "th", "tr" */ |
| 3007 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3007 | + } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3008 | 3008 | array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) { |
| 3009 | 3009 | /* Parse error. Ignore the token. */ |
| 3010 | 3010 | |
@@ -3019,7 +3019,7 @@ discard block |
||
| 3019 | 3019 | $clear = array('tr', 'html'); |
| 3020 | 3020 | |
| 3021 | 3021 | /* A start tag whose tag name is one of: "th", "td" */ |
| 3022 | - if($token['type'] === HTML5::STARTTAG && |
|
| 3022 | + if ($token['type'] === HTML5::STARTTAG && |
|
| 3023 | 3023 | ($token['name'] === 'th' || $token['name'] === 'td')) { |
| 3024 | 3024 | /* Clear the stack back to a table row context. */ |
| 3025 | 3025 | $this->clearStackToTableContext($clear); |
@@ -3034,11 +3034,11 @@ discard block |
||
| 3034 | 3034 | $this->a_formatting[] = self::MARKER; |
| 3035 | 3035 | |
| 3036 | 3036 | /* An end tag whose tag name is "tr" */ |
| 3037 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { |
|
| 3037 | + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { |
|
| 3038 | 3038 | /* If the stack of open elements does not have an element in table |
| 3039 | 3039 | scope with the same tag name as the token, this is a parse error. |
| 3040 | 3040 | Ignore the token. (innerHTML case) */ |
| 3041 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3041 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 3042 | 3042 | // Ignore. |
| 3043 | 3043 | |
| 3044 | 3044 | /* Otherwise: */ |
@@ -3055,7 +3055,7 @@ discard block |
||
| 3055 | 3055 | |
| 3056 | 3056 | /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
| 3057 | 3057 | "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */ |
| 3058 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3058 | + } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3059 | 3059 | array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) { |
| 3060 | 3060 | /* Act as if an end tag with the tag name "tr" had been seen, then, |
| 3061 | 3061 | if that token wasn't ignored, reprocess the current token. */ |
@@ -3067,12 +3067,12 @@ discard block |
||
| 3067 | 3067 | return $this->inCell($token); |
| 3068 | 3068 | |
| 3069 | 3069 | /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ |
| 3070 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3070 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 3071 | 3071 | in_array($token['name'], array('tbody', 'tfoot', 'thead'))) { |
| 3072 | 3072 | /* If the stack of open elements does not have an element in table |
| 3073 | 3073 | scope with the same tag name as the token, this is a parse error. |
| 3074 | 3074 | Ignore the token. */ |
| 3075 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3075 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 3076 | 3076 | // Ignore. |
| 3077 | 3077 | |
| 3078 | 3078 | /* Otherwise: */ |
@@ -3089,7 +3089,7 @@ discard block |
||
| 3089 | 3089 | |
| 3090 | 3090 | /* An end tag whose tag name is one of: "body", "caption", "col", |
| 3091 | 3091 | "colgroup", "html", "td", "th" */ |
| 3092 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3092 | + } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3093 | 3093 | array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) { |
| 3094 | 3094 | /* Parse error. Ignore the token. */ |
| 3095 | 3095 | |
@@ -3102,12 +3102,12 @@ discard block |
||
| 3102 | 3102 | |
| 3103 | 3103 | private function inCell($token) { |
| 3104 | 3104 | /* An end tag whose tag name is one of: "td", "th" */ |
| 3105 | - if($token['type'] === HTML5::ENDTAG && |
|
| 3105 | + if ($token['type'] === HTML5::ENDTAG && |
|
| 3106 | 3106 | ($token['name'] === 'td' || $token['name'] === 'th')) { |
| 3107 | 3107 | /* If the stack of open elements does not have an element in table |
| 3108 | 3108 | scope with the same tag name as that of the token, then this is a |
| 3109 | 3109 | parse error and the token must be ignored. */ |
| 3110 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3110 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 3111 | 3111 | // Ignore. |
| 3112 | 3112 | |
| 3113 | 3113 | /* Otherwise: */ |
@@ -3122,11 +3122,11 @@ discard block |
||
| 3122 | 3122 | |
| 3123 | 3123 | /* Pop elements from this stack until an element with the same |
| 3124 | 3124 | tag name as the token has been popped from the stack. */ |
| 3125 | - while(true) { |
|
| 3125 | + while (true) { |
|
| 3126 | 3126 | $node = end($this->stack)->nodeName; |
| 3127 | 3127 | array_pop($this->stack); |
| 3128 | 3128 | |
| 3129 | - if($node === $token['name']) { |
|
| 3129 | + if ($node === $token['name']) { |
|
| 3130 | 3130 | break; |
| 3131 | 3131 | } |
| 3132 | 3132 | } |
@@ -3142,13 +3142,13 @@ discard block |
||
| 3142 | 3142 | |
| 3143 | 3143 | /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
| 3144 | 3144 | "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 3145 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3145 | + } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3146 | 3146 | array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
| 3147 | 3147 | 'thead', 'tr'))) { |
| 3148 | 3148 | /* If the stack of open elements does not have a td or th element |
| 3149 | 3149 | in table scope, then this is a parse error; ignore the token. |
| 3150 | 3150 | (innerHTML case) */ |
| 3151 | - if(!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3151 | + if (!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3152 | 3152 | // Ignore. |
| 3153 | 3153 | |
| 3154 | 3154 | /* Otherwise, close the cell (see below) and reprocess the current |
@@ -3160,13 +3160,13 @@ discard block |
||
| 3160 | 3160 | |
| 3161 | 3161 | /* A start tag whose tag name is one of: "caption", "col", "colgroup", |
| 3162 | 3162 | "tbody", "td", "tfoot", "th", "thead", "tr" */ |
| 3163 | - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3163 | + } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'], |
|
| 3164 | 3164 | array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', |
| 3165 | 3165 | 'thead', 'tr'))) { |
| 3166 | 3166 | /* If the stack of open elements does not have a td or th element |
| 3167 | 3167 | in table scope, then this is a parse error; ignore the token. |
| 3168 | 3168 | (innerHTML case) */ |
| 3169 | - if(!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3169 | + if (!$this->elementInScope(array('td', 'th'), true)) { |
|
| 3170 | 3170 | // Ignore. |
| 3171 | 3171 | |
| 3172 | 3172 | /* Otherwise, close the cell (see below) and reprocess the current |
@@ -3178,19 +3178,19 @@ discard block |
||
| 3178 | 3178 | |
| 3179 | 3179 | /* An end tag whose tag name is one of: "body", "caption", "col", |
| 3180 | 3180 | "colgroup", "html" */ |
| 3181 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3181 | + } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3182 | 3182 | array('body', 'caption', 'col', 'colgroup', 'html'))) { |
| 3183 | 3183 | /* Parse error. Ignore the token. */ |
| 3184 | 3184 | |
| 3185 | 3185 | /* An end tag whose tag name is one of: "table", "tbody", "tfoot", |
| 3186 | 3186 | "thead", "tr" */ |
| 3187 | - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3187 | + } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'], |
|
| 3188 | 3188 | array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { |
| 3189 | 3189 | /* If the stack of open elements does not have an element in table |
| 3190 | 3190 | scope with the same tag name as that of the token (which can only |
| 3191 | 3191 | happen for "tbody", "tfoot" and "thead", or, in the innerHTML case), |
| 3192 | 3192 | then this is a parse error and the token must be ignored. */ |
| 3193 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3193 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 3194 | 3194 | // Ignore. |
| 3195 | 3195 | |
| 3196 | 3196 | /* Otherwise, close the cell (see below) and reprocess the current |
@@ -3211,22 +3211,22 @@ discard block |
||
| 3211 | 3211 | /* Handle the token as follows: */ |
| 3212 | 3212 | |
| 3213 | 3213 | /* A character token */ |
| 3214 | - if($token['type'] === HTML5::CHARACTR) { |
|
| 3214 | + if ($token['type'] === HTML5::CHARACTR) { |
|
| 3215 | 3215 | /* Append the token's character to the current node. */ |
| 3216 | 3216 | $this->insertText($token['data']); |
| 3217 | 3217 | |
| 3218 | 3218 | /* A comment token */ |
| 3219 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3219 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 3220 | 3220 | /* Append a Comment node to the current node with the data |
| 3221 | 3221 | attribute set to the data given in the comment token. */ |
| 3222 | 3222 | $this->insertComment($token['data']); |
| 3223 | 3223 | |
| 3224 | 3224 | /* A start tag token whose tag name is "option" */ |
| 3225 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 3225 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 3226 | 3226 | $token['name'] === 'option') { |
| 3227 | 3227 | /* If the current node is an option element, act as if an end tag |
| 3228 | 3228 | with the tag name "option" had been seen. */ |
| 3229 | - if(end($this->stack)->nodeName === 'option') { |
|
| 3229 | + if (end($this->stack)->nodeName === 'option') { |
|
| 3230 | 3230 | $this->inSelect(array( |
| 3231 | 3231 | 'name' => 'option', |
| 3232 | 3232 | 'type' => HTML5::ENDTAG |
@@ -3237,11 +3237,11 @@ discard block |
||
| 3237 | 3237 | $this->insertElement($token); |
| 3238 | 3238 | |
| 3239 | 3239 | /* A start tag token whose tag name is "optgroup" */ |
| 3240 | - } elseif($token['type'] === HTML5::STARTTAG && |
|
| 3240 | + } elseif ($token['type'] === HTML5::STARTTAG && |
|
| 3241 | 3241 | $token['name'] === 'optgroup') { |
| 3242 | 3242 | /* If the current node is an option element, act as if an end tag |
| 3243 | 3243 | with the tag name "option" had been seen. */ |
| 3244 | - if(end($this->stack)->nodeName === 'option') { |
|
| 3244 | + if (end($this->stack)->nodeName === 'option') { |
|
| 3245 | 3245 | $this->inSelect(array( |
| 3246 | 3246 | 'name' => 'option', |
| 3247 | 3247 | 'type' => HTML5::ENDTAG |
@@ -3250,7 +3250,7 @@ discard block |
||
| 3250 | 3250 | |
| 3251 | 3251 | /* If the current node is an optgroup element, act as if an end tag |
| 3252 | 3252 | with the tag name "optgroup" had been seen. */ |
| 3253 | - if(end($this->stack)->nodeName === 'optgroup') { |
|
| 3253 | + if (end($this->stack)->nodeName === 'optgroup') { |
|
| 3254 | 3254 | $this->inSelect(array( |
| 3255 | 3255 | 'name' => 'optgroup', |
| 3256 | 3256 | 'type' => HTML5::ENDTAG |
@@ -3261,7 +3261,7 @@ discard block |
||
| 3261 | 3261 | $this->insertElement($token); |
| 3262 | 3262 | |
| 3263 | 3263 | /* An end tag token whose tag name is "optgroup" */ |
| 3264 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3264 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 3265 | 3265 | $token['name'] === 'optgroup') { |
| 3266 | 3266 | /* First, if the current node is an option element, and the node |
| 3267 | 3267 | immediately before it in the stack of open elements is an optgroup |
@@ -3269,7 +3269,7 @@ discard block |
||
| 3269 | 3269 | been seen. */ |
| 3270 | 3270 | $elements_in_stack = count($this->stack); |
| 3271 | 3271 | |
| 3272 | - if($this->stack[$elements_in_stack - 1]->nodeName === 'option' && |
|
| 3272 | + if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' && |
|
| 3273 | 3273 | $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') { |
| 3274 | 3274 | $this->inSelect(array( |
| 3275 | 3275 | 'name' => 'option', |
@@ -3280,38 +3280,38 @@ discard block |
||
| 3280 | 3280 | /* If the current node is an optgroup element, then pop that node |
| 3281 | 3281 | from the stack of open elements. Otherwise, this is a parse error, |
| 3282 | 3282 | ignore the token. */ |
| 3283 | - if($this->stack[$elements_in_stack - 1] === 'optgroup') { |
|
| 3283 | + if ($this->stack[$elements_in_stack - 1] === 'optgroup') { |
|
| 3284 | 3284 | array_pop($this->stack); |
| 3285 | 3285 | } |
| 3286 | 3286 | |
| 3287 | 3287 | /* An end tag token whose tag name is "option" */ |
| 3288 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3288 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 3289 | 3289 | $token['name'] === 'option') { |
| 3290 | 3290 | /* If the current node is an option element, then pop that node |
| 3291 | 3291 | from the stack of open elements. Otherwise, this is a parse error, |
| 3292 | 3292 | ignore the token. */ |
| 3293 | - if(end($this->stack)->nodeName === 'option') { |
|
| 3293 | + if (end($this->stack)->nodeName === 'option') { |
|
| 3294 | 3294 | array_pop($this->stack); |
| 3295 | 3295 | } |
| 3296 | 3296 | |
| 3297 | 3297 | /* An end tag whose tag name is "select" */ |
| 3298 | - } elseif($token['type'] === HTML5::ENDTAG && |
|
| 3298 | + } elseif ($token['type'] === HTML5::ENDTAG && |
|
| 3299 | 3299 | $token['name'] === 'select') { |
| 3300 | 3300 | /* If the stack of open elements does not have an element in table |
| 3301 | 3301 | scope with the same tag name as the token, this is a parse error. |
| 3302 | 3302 | Ignore the token. (innerHTML case) */ |
| 3303 | - if(!$this->elementInScope($token['name'], true)) { |
|
| 3303 | + if (!$this->elementInScope($token['name'], true)) { |
|
| 3304 | 3304 | // w/e |
| 3305 | 3305 | |
| 3306 | 3306 | /* Otherwise: */ |
| 3307 | 3307 | } else { |
| 3308 | 3308 | /* Pop elements from the stack of open elements until a select |
| 3309 | 3309 | element has been popped from the stack. */ |
| 3310 | - while(true) { |
|
| 3310 | + while (true) { |
|
| 3311 | 3311 | $current = end($this->stack)->nodeName; |
| 3312 | 3312 | array_pop($this->stack); |
| 3313 | 3313 | |
| 3314 | - if($current === 'select') { |
|
| 3314 | + if ($current === 'select') { |
|
| 3315 | 3315 | break; |
| 3316 | 3316 | } |
| 3317 | 3317 | } |
@@ -3321,7 +3321,7 @@ discard block |
||
| 3321 | 3321 | } |
| 3322 | 3322 | |
| 3323 | 3323 | /* A start tag whose tag name is "select" */ |
| 3324 | - } elseif($token['name'] === 'select' && |
|
| 3324 | + } elseif ($token['name'] === 'select' && |
|
| 3325 | 3325 | $token['type'] === HTML5::STARTTAG) { |
| 3326 | 3326 | /* Parse error. Act as if the token had been an end tag with the |
| 3327 | 3327 | tag name "select" instead. */ |
@@ -3332,7 +3332,7 @@ discard block |
||
| 3332 | 3332 | |
| 3333 | 3333 | /* An end tag whose tag name is one of: "caption", "table", "tbody", |
| 3334 | 3334 | "tfoot", "thead", "tr", "td", "th" */ |
| 3335 | - } elseif(in_array($token['name'], array('caption', 'table', 'tbody', |
|
| 3335 | + } elseif (in_array($token['name'], array('caption', 'table', 'tbody', |
|
| 3336 | 3336 | 'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) { |
| 3337 | 3337 | /* Parse error. */ |
| 3338 | 3338 | // w/e |
@@ -3341,7 +3341,7 @@ discard block |
||
| 3341 | 3341 | the same tag name as that of the token, then act as if an end tag |
| 3342 | 3342 | with the tag name "select" had been seen, and reprocess the token. |
| 3343 | 3343 | Otherwise, ignore the token. */ |
| 3344 | - if($this->elementInScope($token['name'], true)) { |
|
| 3344 | + if ($this->elementInScope($token['name'], true)) { |
|
| 3345 | 3345 | $this->inSelect(array( |
| 3346 | 3346 | 'name' => 'select', |
| 3347 | 3347 | 'type' => HTML5::ENDTAG |
@@ -3362,14 +3362,14 @@ discard block |
||
| 3362 | 3362 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 3363 | 3363 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3364 | 3364 | or U+0020 SPACE */ |
| 3365 | - if($token['type'] === HTML5::CHARACTR && |
|
| 3365 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 3366 | 3366 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 3367 | 3367 | /* Process the token as it would be processed if the insertion mode |
| 3368 | 3368 | was "in body". */ |
| 3369 | 3369 | $this->inBody($token); |
| 3370 | 3370 | |
| 3371 | 3371 | /* A comment token */ |
| 3372 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3372 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 3373 | 3373 | /* Append a Comment node to the first element in the stack of open |
| 3374 | 3374 | elements (the html element), with the data attribute set to the |
| 3375 | 3375 | data given in the comment token. */ |
@@ -3377,7 +3377,7 @@ discard block |
||
| 3377 | 3377 | $this->stack[0]->appendChild($comment); |
| 3378 | 3378 | |
| 3379 | 3379 | /* An end tag with the tag name "html" */ |
| 3380 | - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') { |
|
| 3380 | + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') { |
|
| 3381 | 3381 | /* If the parser was originally created in order to handle the |
| 3382 | 3382 | setting of an element's innerHTML attribute, this is a parse error; |
| 3383 | 3383 | ignore the token. (The element will be an html element in this |
@@ -3401,28 +3401,28 @@ discard block |
||
| 3401 | 3401 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 3402 | 3402 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3403 | 3403 | U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ |
| 3404 | - if($token['type'] === HTML5::CHARACTR && |
|
| 3404 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 3405 | 3405 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 3406 | 3406 | /* Append the character to the current node. */ |
| 3407 | 3407 | $this->insertText($token['data']); |
| 3408 | 3408 | |
| 3409 | 3409 | /* A comment token */ |
| 3410 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3410 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 3411 | 3411 | /* Append a Comment node to the current node with the data |
| 3412 | 3412 | attribute set to the data given in the comment token. */ |
| 3413 | 3413 | $this->insertComment($token['data']); |
| 3414 | 3414 | |
| 3415 | 3415 | /* A start tag with the tag name "frameset" */ |
| 3416 | - } elseif($token['name'] === 'frameset' && |
|
| 3416 | + } elseif ($token['name'] === 'frameset' && |
|
| 3417 | 3417 | $token['type'] === HTML5::STARTTAG) { |
| 3418 | 3418 | $this->insertElement($token); |
| 3419 | 3419 | |
| 3420 | 3420 | /* An end tag with the tag name "frameset" */ |
| 3421 | - } elseif($token['name'] === 'frameset' && |
|
| 3421 | + } elseif ($token['name'] === 'frameset' && |
|
| 3422 | 3422 | $token['type'] === HTML5::ENDTAG) { |
| 3423 | 3423 | /* If the current node is the root html element, then this is a |
| 3424 | 3424 | parse error; ignore the token. (innerHTML case) */ |
| 3425 | - if(end($this->stack)->nodeName === 'html') { |
|
| 3425 | + if (end($this->stack)->nodeName === 'html') { |
|
| 3426 | 3426 | // Ignore |
| 3427 | 3427 | |
| 3428 | 3428 | } else { |
@@ -3438,7 +3438,7 @@ discard block |
||
| 3438 | 3438 | } |
| 3439 | 3439 | |
| 3440 | 3440 | /* A start tag with the tag name "frame" */ |
| 3441 | - } elseif($token['name'] === 'frame' && |
|
| 3441 | + } elseif ($token['name'] === 'frame' && |
|
| 3442 | 3442 | $token['type'] === HTML5::STARTTAG) { |
| 3443 | 3443 | /* Insert an HTML element for the token. */ |
| 3444 | 3444 | $this->insertElement($token); |
@@ -3447,7 +3447,7 @@ discard block |
||
| 3447 | 3447 | array_pop($this->stack); |
| 3448 | 3448 | |
| 3449 | 3449 | /* A start tag with the tag name "noframes" */ |
| 3450 | - } elseif($token['name'] === 'noframes' && |
|
| 3450 | + } elseif ($token['name'] === 'noframes' && |
|
| 3451 | 3451 | $token['type'] === HTML5::STARTTAG) { |
| 3452 | 3452 | /* Process the token as if the insertion mode had been "in body". */ |
| 3453 | 3453 | $this->inBody($token); |
@@ -3464,25 +3464,25 @@ discard block |
||
| 3464 | 3464 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 3465 | 3465 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3466 | 3466 | U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ |
| 3467 | - if($token['type'] === HTML5::CHARACTR && |
|
| 3467 | + if ($token['type'] === HTML5::CHARACTR && |
|
| 3468 | 3468 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 3469 | 3469 | /* Append the character to the current node. */ |
| 3470 | 3470 | $this->insertText($token['data']); |
| 3471 | 3471 | |
| 3472 | 3472 | /* A comment token */ |
| 3473 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3473 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 3474 | 3474 | /* Append a Comment node to the current node with the data |
| 3475 | 3475 | attribute set to the data given in the comment token. */ |
| 3476 | 3476 | $this->insertComment($token['data']); |
| 3477 | 3477 | |
| 3478 | 3478 | /* An end tag with the tag name "html" */ |
| 3479 | - } elseif($token['name'] === 'html' && |
|
| 3479 | + } elseif ($token['name'] === 'html' && |
|
| 3480 | 3480 | $token['type'] === HTML5::ENDTAG) { |
| 3481 | 3481 | /* Switch to the trailing end phase. */ |
| 3482 | 3482 | $this->phase = self::END_PHASE; |
| 3483 | 3483 | |
| 3484 | 3484 | /* A start tag with the tag name "noframes" */ |
| 3485 | - } elseif($token['name'] === 'noframes' && |
|
| 3485 | + } elseif ($token['name'] === 'noframes' && |
|
| 3486 | 3486 | $token['type'] === HTML5::STARTTAG) { |
| 3487 | 3487 | /* Process the token as if the insertion mode had been "in body". */ |
| 3488 | 3488 | $this->inBody($token); |
@@ -3498,11 +3498,11 @@ discard block |
||
| 3498 | 3498 | stage, it must be processed as described in this section. */ |
| 3499 | 3499 | |
| 3500 | 3500 | /* A DOCTYPE token */ |
| 3501 | - if($token['type'] === HTML5::DOCTYPE) { |
|
| 3501 | + if ($token['type'] === HTML5::DOCTYPE) { |
|
| 3502 | 3502 | // Parse error. Ignore the token. |
| 3503 | 3503 | |
| 3504 | 3504 | /* A comment token */ |
| 3505 | - } elseif($token['type'] === HTML5::COMMENT) { |
|
| 3505 | + } elseif ($token['type'] === HTML5::COMMENT) { |
|
| 3506 | 3506 | /* Append a Comment node to the Document object with the data |
| 3507 | 3507 | attribute set to the data given in the comment token. */ |
| 3508 | 3508 | $comment = $this->dom->createComment($token['data']); |
@@ -3511,7 +3511,7 @@ discard block |
||
| 3511 | 3511 | /* A character token that is one of one of U+0009 CHARACTER TABULATION, |
| 3512 | 3512 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3513 | 3513 | or U+0020 SPACE */ |
| 3514 | - } elseif($token['type'] === HTML5::CHARACTR && |
|
| 3514 | + } elseif ($token['type'] === HTML5::CHARACTR && |
|
| 3515 | 3515 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { |
| 3516 | 3516 | /* Process the token as it would be processed in the main phase. */ |
| 3517 | 3517 | $this->mainPhase($token); |
@@ -3519,7 +3519,7 @@ discard block |
||
| 3519 | 3519 | /* A character token that is not one of U+0009 CHARACTER TABULATION, |
| 3520 | 3520 | U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), |
| 3521 | 3521 | or U+0020 SPACE. Or a start tag token. Or an end tag token. */ |
| 3522 | - } elseif(($token['type'] === HTML5::CHARACTR && |
|
| 3522 | + } elseif (($token['type'] === HTML5::CHARACTR && |
|
| 3523 | 3523 | preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || |
| 3524 | 3524 | $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) { |
| 3525 | 3525 | /* Parse error. Switch back to the main phase and reprocess the |
@@ -3528,7 +3528,7 @@ discard block |
||
| 3528 | 3528 | return $this->mainPhase($token); |
| 3529 | 3529 | |
| 3530 | 3530 | /* An end-of-file token */ |
| 3531 | - } elseif($token['type'] === HTML5::EOF) { |
|
| 3531 | + } elseif ($token['type'] === HTML5::EOF) { |
|
| 3532 | 3532 | /* OMG DONE!! */ |
| 3533 | 3533 | } |
| 3534 | 3534 | } |
@@ -3547,8 +3547,8 @@ discard block |
||
| 3547 | 3547 | |
| 3548 | 3548 | $el = $this->dom->createElement($token['name']); |
| 3549 | 3549 | |
| 3550 | - foreach($token['attr'] as $attr) { |
|
| 3551 | - if(!$el->hasAttribute($attr['name'])) { |
|
| 3550 | + foreach ($token['attr'] as $attr) { |
|
| 3551 | + if (!$el->hasAttribute($attr['name'])) { |
|
| 3552 | 3552 | $el->setAttribute($attr['name'], $attr['value']); |
| 3553 | 3553 | } |
| 3554 | 3554 | } |
@@ -3570,25 +3570,25 @@ discard block |
||
| 3570 | 3570 | } |
| 3571 | 3571 | |
| 3572 | 3572 | private function appendToRealParent($node) { |
| 3573 | - if($this->foster_parent === null) { |
|
| 3573 | + if ($this->foster_parent === null) { |
|
| 3574 | 3574 | end($this->stack)->appendChild($node); |
| 3575 | 3575 | |
| 3576 | - } elseif($this->foster_parent !== null) { |
|
| 3576 | + } elseif ($this->foster_parent !== null) { |
|
| 3577 | 3577 | /* If the foster parent element is the parent element of the |
| 3578 | 3578 | last table element in the stack of open elements, then the new |
| 3579 | 3579 | node must be inserted immediately before the last table element |
| 3580 | 3580 | in the stack of open elements in the foster parent element; |
| 3581 | 3581 | otherwise, the new node must be appended to the foster parent |
| 3582 | 3582 | element. */ |
| 3583 | - for($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 3584 | - if($this->stack[$n]->nodeName === 'table' && |
|
| 3583 | + for ($n = count($this->stack) - 1; $n >= 0; $n--) { |
|
| 3584 | + if ($this->stack[$n]->nodeName === 'table' && |
|
| 3585 | 3585 | $this->stack[$n]->parentNode !== null) { |
| 3586 | 3586 | $table = $this->stack[$n]; |
| 3587 | 3587 | break; |
| 3588 | 3588 | } |
| 3589 | 3589 | } |
| 3590 | 3590 | |
| 3591 | - if(isset($table) && $this->foster_parent->isSameNode($table->parentNode)) |
|
| 3591 | + if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) |
|
| 3592 | 3592 | $this->foster_parent->insertBefore($node, $table); |
| 3593 | 3593 | else |
| 3594 | 3594 | $this->foster_parent->appendChild($node); |
@@ -3598,9 +3598,9 @@ discard block |
||
| 3598 | 3598 | } |
| 3599 | 3599 | |
| 3600 | 3600 | private function elementInScope($el, $table = false) { |
| 3601 | - if(is_array($el)) { |
|
| 3602 | - foreach($el as $element) { |
|
| 3603 | - if($this->elementInScope($element, $table)) { |
|
| 3601 | + if (is_array($el)) { |
|
| 3602 | + foreach ($el as $element) { |
|
| 3603 | + if ($this->elementInScope($element, $table)) { |
|
| 3604 | 3604 | return true; |
| 3605 | 3605 | } |
| 3606 | 3606 | } |
@@ -3610,28 +3610,28 @@ discard block |
||
| 3610 | 3610 | |
| 3611 | 3611 | $leng = count($this->stack); |
| 3612 | 3612 | |
| 3613 | - for($n = 0; $n < $leng; $n++) { |
|
| 3613 | + for ($n = 0; $n < $leng; $n++) { |
|
| 3614 | 3614 | /* 1. Initialise node to be the current node (the bottommost node of |
| 3615 | 3615 | the stack). */ |
| 3616 | 3616 | $node = $this->stack[$leng - 1 - $n]; |
| 3617 | 3617 | |
| 3618 | - if($node->tagName === $el) { |
|
| 3618 | + if ($node->tagName === $el) { |
|
| 3619 | 3619 | /* 2. If node is the target node, terminate in a match state. */ |
| 3620 | 3620 | return true; |
| 3621 | 3621 | |
| 3622 | - } elseif($node->tagName === 'table') { |
|
| 3622 | + } elseif ($node->tagName === 'table') { |
|
| 3623 | 3623 | /* 3. Otherwise, if node is a table element, terminate in a failure |
| 3624 | 3624 | state. */ |
| 3625 | 3625 | return false; |
| 3626 | 3626 | |
| 3627 | - } elseif($table === true && in_array($node->tagName, array('caption', 'td', |
|
| 3627 | + } elseif ($table === true && in_array($node->tagName, array('caption', 'td', |
|
| 3628 | 3628 | 'th', 'button', 'marquee', 'object'))) { |
| 3629 | 3629 | /* 4. Otherwise, if the algorithm is the "has an element in scope" |
| 3630 | 3630 | variant (rather than the "has an element in table scope" variant), |
| 3631 | 3631 | and node is one of the following, terminate in a failure state. */ |
| 3632 | 3632 | return false; |
| 3633 | 3633 | |
| 3634 | - } elseif($node === $node->ownerDocument->documentElement) { |
|
| 3634 | + } elseif ($node === $node->ownerDocument->documentElement) { |
|
| 3635 | 3635 | /* 5. Otherwise, if node is an html element (root element), terminate |
| 3636 | 3636 | in a failure state. (This can only happen if the node is the topmost |
| 3637 | 3637 | node of the stack of open elements, and prevents the next step from |
@@ -3651,7 +3651,7 @@ discard block |
||
| 3651 | 3651 | then there is nothing to reconstruct; stop this algorithm. */ |
| 3652 | 3652 | $formatting_elements = count($this->a_formatting); |
| 3653 | 3653 | |
| 3654 | - if($formatting_elements === 0) { |
|
| 3654 | + if ($formatting_elements === 0) { |
|
| 3655 | 3655 | return false; |
| 3656 | 3656 | } |
| 3657 | 3657 | |
@@ -3663,14 +3663,14 @@ discard block |
||
| 3663 | 3663 | formatting elements is a marker, or if it is an element that is in the |
| 3664 | 3664 | stack of open elements, then there is nothing to reconstruct; stop this |
| 3665 | 3665 | algorithm. */ |
| 3666 | - if($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3666 | + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3667 | 3667 | return false; |
| 3668 | 3668 | } |
| 3669 | 3669 | |
| 3670 | - for($a = $formatting_elements - 1; $a >= 0; true) { |
|
| 3670 | + for ($a = $formatting_elements - 1; $a >= 0; true) { |
|
| 3671 | 3671 | /* 4. If there are no entries before entry in the list of active |
| 3672 | 3672 | formatting elements, then jump to step 8. */ |
| 3673 | - if($a === 0) { |
|
| 3673 | + if ($a === 0) { |
|
| 3674 | 3674 | $step_seven = false; |
| 3675 | 3675 | break; |
| 3676 | 3676 | } |
@@ -3682,15 +3682,15 @@ discard block |
||
| 3682 | 3682 | |
| 3683 | 3683 | /* 6. If entry is neither a marker nor an element that is also in |
| 3684 | 3684 | thetack of open elements, go to step 4. */ |
| 3685 | - if($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3685 | + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { |
|
| 3686 | 3686 | break; |
| 3687 | 3687 | } |
| 3688 | 3688 | } |
| 3689 | 3689 | |
| 3690 | - while(true) { |
|
| 3690 | + while (true) { |
|
| 3691 | 3691 | /* 7. Let entry be the element one later than entry in the list of |
| 3692 | 3692 | active formatting elements. */ |
| 3693 | - if(isset($step_seven) && $step_seven === true) { |
|
| 3693 | + if (isset($step_seven) && $step_seven === true) { |
|
| 3694 | 3694 | $a++; |
| 3695 | 3695 | $entry = $this->a_formatting[$a]; |
| 3696 | 3696 | } |
@@ -3709,7 +3709,7 @@ discard block |
||
| 3709 | 3709 | |
| 3710 | 3710 | /* 11. If the entry for clone in the list of active formatting |
| 3711 | 3711 | elements is not the last entry in the list, return to step 7. */ |
| 3712 | - if(end($this->a_formatting) !== $clone) { |
|
| 3712 | + if (end($this->a_formatting) !== $clone) { |
|
| 3713 | 3713 | $step_seven = true; |
| 3714 | 3714 | } else { |
| 3715 | 3715 | break; |
@@ -3722,7 +3722,7 @@ discard block |
||
| 3722 | 3722 | formatting elements up to the last marker, the UA must perform the |
| 3723 | 3723 | following steps: */ |
| 3724 | 3724 | |
| 3725 | - while(true) { |
|
| 3725 | + while (true) { |
|
| 3726 | 3726 | /* 1. Let entry be the last (most recently added) entry in the list |
| 3727 | 3727 | of active formatting elements. */ |
| 3728 | 3728 | $entry = end($this->a_formatting); |
@@ -3732,7 +3732,7 @@ discard block |
||
| 3732 | 3732 | |
| 3733 | 3733 | /* 3. If entry was a marker, then stop the algorithm at this point. |
| 3734 | 3734 | The list has been cleared up to the last marker. */ |
| 3735 | - if($entry === self::MARKER) { |
|
| 3735 | + if ($entry === self::MARKER) { |
|
| 3736 | 3736 | break; |
| 3737 | 3737 | } |
| 3738 | 3738 | } |
@@ -3747,20 +3747,20 @@ discard block |
||
| 3747 | 3747 | $node = end($this->stack); |
| 3748 | 3748 | $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude); |
| 3749 | 3749 | |
| 3750 | - while(in_array(end($this->stack)->nodeName, $elements)) { |
|
| 3750 | + while (in_array(end($this->stack)->nodeName, $elements)) { |
|
| 3751 | 3751 | array_pop($this->stack); |
| 3752 | 3752 | } |
| 3753 | 3753 | } |
| 3754 | 3754 | |
| 3755 | 3755 | private function getElementCategory($node) { |
| 3756 | 3756 | $name = $node->tagName; |
| 3757 | - if(in_array($name, $this->special)) |
|
| 3757 | + if (in_array($name, $this->special)) |
|
| 3758 | 3758 | return self::SPECIAL; |
| 3759 | 3759 | |
| 3760 | - elseif(in_array($name, $this->scoping)) |
|
| 3760 | + elseif (in_array($name, $this->scoping)) |
|
| 3761 | 3761 | return self::SCOPING; |
| 3762 | 3762 | |
| 3763 | - elseif(in_array($name, $this->formatting)) |
|
| 3763 | + elseif (in_array($name, $this->formatting)) |
|
| 3764 | 3764 | return self::FORMATTING; |
| 3765 | 3765 | |
| 3766 | 3766 | else |
@@ -3773,10 +3773,10 @@ discard block |
||
| 3773 | 3773 | a table element or an html element, pop elements from the stack of open |
| 3774 | 3774 | elements. If this causes any elements to be popped from the stack, then |
| 3775 | 3775 | this is a parse error. */ |
| 3776 | - while(true) { |
|
| 3776 | + while (true) { |
|
| 3777 | 3777 | $node = end($this->stack)->nodeName; |
| 3778 | 3778 | |
| 3779 | - if(in_array($node, $elements)) { |
|
| 3779 | + if (in_array($node, $elements)) { |
|
| 3780 | 3780 | break; |
| 3781 | 3781 | } else { |
| 3782 | 3782 | array_pop($this->stack); |
@@ -3789,7 +3789,7 @@ discard block |
||
| 3789 | 3789 | $last = false; |
| 3790 | 3790 | $leng = count($this->stack); |
| 3791 | 3791 | |
| 3792 | - for($n = $leng - 1; $n >= 0; $n--) { |
|
| 3792 | + for ($n = $leng - 1; $n >= 0; $n--) { |
|
| 3793 | 3793 | /* 2. Let node be the last node in the stack of open elements. */ |
| 3794 | 3794 | $node = $this->stack[$n]; |
| 3795 | 3795 | |
@@ -3797,68 +3797,68 @@ discard block |
||
| 3797 | 3797 | set last to true. If the element whose innerHTML attribute is being |
| 3798 | 3798 | set is neither a td element nor a th element, then set node to the |
| 3799 | 3799 | element whose innerHTML attribute is being set. (innerHTML case) */ |
| 3800 | - if($this->stack[0]->isSameNode($node)) { |
|
| 3800 | + if ($this->stack[0]->isSameNode($node)) { |
|
| 3801 | 3801 | $last = true; |
| 3802 | 3802 | } |
| 3803 | 3803 | |
| 3804 | 3804 | /* 4. If node is a select element, then switch the insertion mode to |
| 3805 | 3805 | "in select" and abort these steps. (innerHTML case) */ |
| 3806 | - if($node->nodeName === 'select') { |
|
| 3806 | + if ($node->nodeName === 'select') { |
|
| 3807 | 3807 | $this->mode = self::IN_SELECT; |
| 3808 | 3808 | break; |
| 3809 | 3809 | |
| 3810 | 3810 | /* 5. If node is a td or th element, then switch the insertion mode |
| 3811 | 3811 | to "in cell" and abort these steps. */ |
| 3812 | - } elseif($node->nodeName === 'td' || $node->nodeName === 'th') { |
|
| 3812 | + } elseif ($node->nodeName === 'td' || $node->nodeName === 'th') { |
|
| 3813 | 3813 | $this->mode = self::IN_CELL; |
| 3814 | 3814 | break; |
| 3815 | 3815 | |
| 3816 | 3816 | /* 6. If node is a tr element, then switch the insertion mode to |
| 3817 | 3817 | "in row" and abort these steps. */ |
| 3818 | - } elseif($node->nodeName === 'tr') { |
|
| 3818 | + } elseif ($node->nodeName === 'tr') { |
|
| 3819 | 3819 | $this->mode = self::IN_ROW; |
| 3820 | 3820 | break; |
| 3821 | 3821 | |
| 3822 | 3822 | /* 7. If node is a tbody, thead, or tfoot element, then switch the |
| 3823 | 3823 | insertion mode to "in table body" and abort these steps. */ |
| 3824 | - } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) { |
|
| 3824 | + } elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) { |
|
| 3825 | 3825 | $this->mode = self::IN_TBODY; |
| 3826 | 3826 | break; |
| 3827 | 3827 | |
| 3828 | 3828 | /* 8. If node is a caption element, then switch the insertion mode |
| 3829 | 3829 | to "in caption" and abort these steps. */ |
| 3830 | - } elseif($node->nodeName === 'caption') { |
|
| 3830 | + } elseif ($node->nodeName === 'caption') { |
|
| 3831 | 3831 | $this->mode = self::IN_CAPTION; |
| 3832 | 3832 | break; |
| 3833 | 3833 | |
| 3834 | 3834 | /* 9. If node is a colgroup element, then switch the insertion mode |
| 3835 | 3835 | to "in column group" and abort these steps. (innerHTML case) */ |
| 3836 | - } elseif($node->nodeName === 'colgroup') { |
|
| 3836 | + } elseif ($node->nodeName === 'colgroup') { |
|
| 3837 | 3837 | $this->mode = self::IN_CGROUP; |
| 3838 | 3838 | break; |
| 3839 | 3839 | |
| 3840 | 3840 | /* 10. If node is a table element, then switch the insertion mode |
| 3841 | 3841 | to "in table" and abort these steps. */ |
| 3842 | - } elseif($node->nodeName === 'table') { |
|
| 3842 | + } elseif ($node->nodeName === 'table') { |
|
| 3843 | 3843 | $this->mode = self::IN_TABLE; |
| 3844 | 3844 | break; |
| 3845 | 3845 | |
| 3846 | 3846 | /* 11. If node is a head element, then switch the insertion mode |
| 3847 | 3847 | to "in body" ("in body"! not "in head"!) and abort these steps. |
| 3848 | 3848 | (innerHTML case) */ |
| 3849 | - } elseif($node->nodeName === 'head') { |
|
| 3849 | + } elseif ($node->nodeName === 'head') { |
|
| 3850 | 3850 | $this->mode = self::IN_BODY; |
| 3851 | 3851 | break; |
| 3852 | 3852 | |
| 3853 | 3853 | /* 12. If node is a body element, then switch the insertion mode to |
| 3854 | 3854 | "in body" and abort these steps. */ |
| 3855 | - } elseif($node->nodeName === 'body') { |
|
| 3855 | + } elseif ($node->nodeName === 'body') { |
|
| 3856 | 3856 | $this->mode = self::IN_BODY; |
| 3857 | 3857 | break; |
| 3858 | 3858 | |
| 3859 | 3859 | /* 13. If node is a frameset element, then switch the insertion |
| 3860 | 3860 | mode to "in frameset" and abort these steps. (innerHTML case) */ |
| 3861 | - } elseif($node->nodeName === 'frameset') { |
|
| 3861 | + } elseif ($node->nodeName === 'frameset') { |
|
| 3862 | 3862 | $this->mode = self::IN_FRAME; |
| 3863 | 3863 | break; |
| 3864 | 3864 | |
@@ -3866,7 +3866,7 @@ discard block |
||
| 3866 | 3866 | pointer is null, switch the insertion mode to "before head", |
| 3867 | 3867 | otherwise, switch the insertion mode to "after head". In either |
| 3868 | 3868 | case, abort these steps. (innerHTML case) */ |
| 3869 | - } elseif($node->nodeName === 'html') { |
|
| 3869 | + } elseif ($node->nodeName === 'html') { |
|
| 3870 | 3870 | $this->mode = ($this->head_pointer === null) |
| 3871 | 3871 | ? self::BEFOR_HEAD |
| 3872 | 3872 | : self::AFTER_HEAD; |
@@ -3875,7 +3875,7 @@ discard block |
||
| 3875 | 3875 | |
| 3876 | 3876 | /* 15. If last is true, then set the insertion mode to "in body" |
| 3877 | 3877 | and abort these steps. (innerHTML case) */ |
| 3878 | - } elseif($last) { |
|
| 3878 | + } elseif ($last) { |
|
| 3879 | 3879 | $this->mode = self::IN_BODY; |
| 3880 | 3880 | break; |
| 3881 | 3881 | } |
@@ -3885,8 +3885,8 @@ discard block |
||
| 3885 | 3885 | private function closeCell() { |
| 3886 | 3886 | /* If the stack of open elements has a td or th element in table scope, |
| 3887 | 3887 | then act as if an end tag token with that tag name had been seen. */ |
| 3888 | - foreach(array('td', 'th') as $cell) { |
|
| 3889 | - if($this->elementInScope($cell, true)) { |
|
| 3888 | + foreach (array('td', 'th') as $cell) { |
|
| 3889 | + if ($this->elementInScope($cell, true)) { |
|
| 3890 | 3890 | $this->inCell(array( |
| 3891 | 3891 | 'name' => $cell, |
| 3892 | 3892 | 'type' => HTML5::ENDTAG |
@@ -60,7 +60,7 @@ discard block |
||
| 60 | 60 | |
| 61 | 61 | /** |
| 62 | 62 | * Prints a complete element with content inside |
| 63 | - * @param $tag Tag name |
|
| 63 | + * @param string $tag Tag name |
|
| 64 | 64 | * @param $contents Element contents |
| 65 | 65 | * @param $attr Tag attributes |
| 66 | 66 | * @param $escape Bool whether or not to escape contents |
@@ -71,6 +71,9 @@ discard block |
||
| 71 | 71 | $this->end($tag); |
| 72 | 72 | } |
| 73 | 73 | |
| 74 | + /** |
|
| 75 | + * @param string $tag |
|
| 76 | + */ |
|
| 74 | 77 | protected function elementEmpty($tag, $attr = array()) { |
| 75 | 78 | return $this->generator->generateFromToken( |
| 76 | 79 | new HTMLPurifier_Token_Empty($tag, $attr) |
@@ -6,170 +6,170 @@ |
||
| 6 | 6 | class HTMLPurifier_Printer |
| 7 | 7 | { |
| 8 | 8 | |
| 9 | - /** |
|
| 10 | - * Instance of HTMLPurifier_Generator for HTML generation convenience funcs |
|
| 11 | - */ |
|
| 12 | - protected $generator; |
|
| 13 | - |
|
| 14 | - /** |
|
| 15 | - * Instance of HTMLPurifier_Config, for easy access |
|
| 16 | - */ |
|
| 17 | - protected $config; |
|
| 18 | - |
|
| 19 | - /** |
|
| 20 | - * Initialize $generator. |
|
| 21 | - */ |
|
| 22 | - public function __construct() { |
|
| 23 | - } |
|
| 24 | - |
|
| 25 | - /** |
|
| 26 | - * Give generator necessary configuration if possible |
|
| 27 | - */ |
|
| 28 | - public function prepareGenerator($config) { |
|
| 29 | - $all = $config->getAll(); |
|
| 30 | - $context = new HTMLPurifier_Context(); |
|
| 31 | - $this->generator = new HTMLPurifier_Generator($config, $context); |
|
| 32 | - } |
|
| 33 | - |
|
| 34 | - /** |
|
| 35 | - * Main function that renders object or aspect of that object |
|
| 36 | - * @note Parameters vary depending on printer |
|
| 37 | - */ |
|
| 38 | - // function render() {} |
|
| 39 | - |
|
| 40 | - /** |
|
| 41 | - * Returns a start tag |
|
| 42 | - * @param $tag Tag name |
|
| 43 | - * @param $attr Attribute array |
|
| 44 | - */ |
|
| 45 | - protected function start($tag, $attr = array()) { |
|
| 46 | - return $this->generator->generateFromToken( |
|
| 47 | - new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) |
|
| 48 | - ); |
|
| 49 | - } |
|
| 50 | - |
|
| 51 | - /** |
|
| 52 | - * Returns an end teg |
|
| 53 | - * @param $tag Tag name |
|
| 54 | - */ |
|
| 55 | - protected function end($tag) { |
|
| 56 | - return $this->generator->generateFromToken( |
|
| 57 | - new HTMLPurifier_Token_End($tag) |
|
| 58 | - ); |
|
| 59 | - } |
|
| 60 | - |
|
| 61 | - /** |
|
| 62 | - * Prints a complete element with content inside |
|
| 63 | - * @param $tag Tag name |
|
| 64 | - * @param $contents Element contents |
|
| 65 | - * @param $attr Tag attributes |
|
| 66 | - * @param $escape Bool whether or not to escape contents |
|
| 67 | - */ |
|
| 68 | - protected function element($tag, $contents, $attr = array(), $escape = true) { |
|
| 69 | - return $this->start($tag, $attr) . |
|
| 70 | - ($escape ? $this->escape($contents) : $contents) . |
|
| 71 | - $this->end($tag); |
|
| 72 | - } |
|
| 73 | - |
|
| 74 | - protected function elementEmpty($tag, $attr = array()) { |
|
| 75 | - return $this->generator->generateFromToken( |
|
| 76 | - new HTMLPurifier_Token_Empty($tag, $attr) |
|
| 77 | - ); |
|
| 78 | - } |
|
| 79 | - |
|
| 80 | - protected function text($text) { |
|
| 81 | - return $this->generator->generateFromToken( |
|
| 82 | - new HTMLPurifier_Token_Text($text) |
|
| 83 | - ); |
|
| 84 | - } |
|
| 85 | - |
|
| 86 | - /** |
|
| 87 | - * Prints a simple key/value row in a table. |
|
| 88 | - * @param $name Key |
|
| 89 | - * @param $value Value |
|
| 90 | - */ |
|
| 91 | - protected function row($name, $value) { |
|
| 92 | - if (is_bool($value)) $value = $value ? 'On' : 'Off'; |
|
| 93 | - return |
|
| 94 | - $this->start('tr') . "\n" . |
|
| 95 | - $this->element('th', $name) . "\n" . |
|
| 96 | - $this->element('td', $value) . "\n" . |
|
| 97 | - $this->end('tr') |
|
| 98 | - ; |
|
| 99 | - } |
|
| 100 | - |
|
| 101 | - /** |
|
| 102 | - * Escapes a string for HTML output. |
|
| 103 | - * @param $string String to escape |
|
| 104 | - */ |
|
| 105 | - protected function escape($string) { |
|
| 106 | - $string = HTMLPurifier_Encoder::cleanUTF8($string); |
|
| 107 | - $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8', false); |
|
| 108 | - return $string; |
|
| 109 | - } |
|
| 110 | - |
|
| 111 | - /** |
|
| 112 | - * Takes a list of strings and turns them into a single list |
|
| 113 | - * @param $array List of strings |
|
| 114 | - * @param $polite Bool whether or not to add an end before the last |
|
| 115 | - */ |
|
| 116 | - protected function listify($array, $polite = false) { |
|
| 117 | - if (empty($array)) return 'None'; |
|
| 118 | - $ret = ''; |
|
| 119 | - $i = count($array); |
|
| 120 | - foreach ($array as $value) { |
|
| 121 | - $i--; |
|
| 122 | - $ret .= $value; |
|
| 123 | - if ($i > 0 && !($polite && $i == 1)) $ret .= ', '; |
|
| 124 | - if ($polite && $i == 1) $ret .= 'and '; |
|
| 125 | - } |
|
| 126 | - return $ret; |
|
| 127 | - } |
|
| 128 | - |
|
| 129 | - /** |
|
| 130 | - * Retrieves the class of an object without prefixes, as well as metadata |
|
| 131 | - * @param $obj Object to determine class of |
|
| 132 | - * @param $prefix Further prefix to remove |
|
| 133 | - */ |
|
| 134 | - protected function getClass($obj, $sec_prefix = '') { |
|
| 135 | - static $five = null; |
|
| 136 | - if ($five === null) $five = version_compare(PHP_VERSION, '5', '>='); |
|
| 137 | - $prefix = 'HTMLPurifier_' . $sec_prefix; |
|
| 138 | - if (!$five) $prefix = strtolower($prefix); |
|
| 139 | - $class = str_replace($prefix, '', get_class($obj)); |
|
| 140 | - $lclass = strtolower($class); |
|
| 141 | - $class .= '('; |
|
| 142 | - switch ($lclass) { |
|
| 143 | - case 'enum': |
|
| 144 | - $values = array(); |
|
| 145 | - foreach ($obj->valid_values as $value => $bool) { |
|
| 146 | - $values[] = $value; |
|
| 147 | - } |
|
| 148 | - $class .= implode(', ', $values); |
|
| 149 | - break; |
|
| 150 | - case 'css_composite': |
|
| 151 | - $values = array(); |
|
| 152 | - foreach ($obj->defs as $def) { |
|
| 153 | - $values[] = $this->getClass($def, $sec_prefix); |
|
| 154 | - } |
|
| 155 | - $class .= implode(', ', $values); |
|
| 156 | - break; |
|
| 157 | - case 'css_multiple': |
|
| 158 | - $class .= $this->getClass($obj->single, $sec_prefix) . ', '; |
|
| 159 | - $class .= $obj->max; |
|
| 160 | - break; |
|
| 161 | - case 'css_denyelementdecorator': |
|
| 162 | - $class .= $this->getClass($obj->def, $sec_prefix) . ', '; |
|
| 163 | - $class .= $obj->element; |
|
| 164 | - break; |
|
| 165 | - case 'css_importantdecorator': |
|
| 166 | - $class .= $this->getClass($obj->def, $sec_prefix); |
|
| 167 | - if ($obj->allow) $class .= ', !important'; |
|
| 168 | - break; |
|
| 169 | - } |
|
| 170 | - $class .= ')'; |
|
| 171 | - return $class; |
|
| 172 | - } |
|
| 9 | + /** |
|
| 10 | + * Instance of HTMLPurifier_Generator for HTML generation convenience funcs |
|
| 11 | + */ |
|
| 12 | + protected $generator; |
|
| 13 | + |
|
| 14 | + /** |
|
| 15 | + * Instance of HTMLPurifier_Config, for easy access |
|
| 16 | + */ |
|
| 17 | + protected $config; |
|
| 18 | + |
|
| 19 | + /** |
|
| 20 | + * Initialize $generator. |
|
| 21 | + */ |
|
| 22 | + public function __construct() { |
|
| 23 | + } |
|
| 24 | + |
|
| 25 | + /** |
|
| 26 | + * Give generator necessary configuration if possible |
|
| 27 | + */ |
|
| 28 | + public function prepareGenerator($config) { |
|
| 29 | + $all = $config->getAll(); |
|
| 30 | + $context = new HTMLPurifier_Context(); |
|
| 31 | + $this->generator = new HTMLPurifier_Generator($config, $context); |
|
| 32 | + } |
|
| 33 | + |
|
| 34 | + /** |
|
| 35 | + * Main function that renders object or aspect of that object |
|
| 36 | + * @note Parameters vary depending on printer |
|
| 37 | + */ |
|
| 38 | + // function render() {} |
|
| 39 | + |
|
| 40 | + /** |
|
| 41 | + * Returns a start tag |
|
| 42 | + * @param $tag Tag name |
|
| 43 | + * @param $attr Attribute array |
|
| 44 | + */ |
|
| 45 | + protected function start($tag, $attr = array()) { |
|
| 46 | + return $this->generator->generateFromToken( |
|
| 47 | + new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) |
|
| 48 | + ); |
|
| 49 | + } |
|
| 50 | + |
|
| 51 | + /** |
|
| 52 | + * Returns an end teg |
|
| 53 | + * @param $tag Tag name |
|
| 54 | + */ |
|
| 55 | + protected function end($tag) { |
|
| 56 | + return $this->generator->generateFromToken( |
|
| 57 | + new HTMLPurifier_Token_End($tag) |
|
| 58 | + ); |
|
| 59 | + } |
|
| 60 | + |
|
| 61 | + /** |
|
| 62 | + * Prints a complete element with content inside |
|
| 63 | + * @param $tag Tag name |
|
| 64 | + * @param $contents Element contents |
|
| 65 | + * @param $attr Tag attributes |
|
| 66 | + * @param $escape Bool whether or not to escape contents |
|
| 67 | + */ |
|
| 68 | + protected function element($tag, $contents, $attr = array(), $escape = true) { |
|
| 69 | + return $this->start($tag, $attr) . |
|
| 70 | + ($escape ? $this->escape($contents) : $contents) . |
|
| 71 | + $this->end($tag); |
|
| 72 | + } |
|
| 73 | + |
|
| 74 | + protected function elementEmpty($tag, $attr = array()) { |
|
| 75 | + return $this->generator->generateFromToken( |
|
| 76 | + new HTMLPurifier_Token_Empty($tag, $attr) |
|
| 77 | + ); |
|
| 78 | + } |
|
| 79 | + |
|
| 80 | + protected function text($text) { |
|
| 81 | + return $this->generator->generateFromToken( |
|
| 82 | + new HTMLPurifier_Token_Text($text) |
|
| 83 | + ); |
|
| 84 | + } |
|
| 85 | + |
|
| 86 | + /** |
|
| 87 | + * Prints a simple key/value row in a table. |
|
| 88 | + * @param $name Key |
|
| 89 | + * @param $value Value |
|
| 90 | + */ |
|
| 91 | + protected function row($name, $value) { |
|
| 92 | + if (is_bool($value)) $value = $value ? 'On' : 'Off'; |
|
| 93 | + return |
|
| 94 | + $this->start('tr') . "\n" . |
|
| 95 | + $this->element('th', $name) . "\n" . |
|
| 96 | + $this->element('td', $value) . "\n" . |
|
| 97 | + $this->end('tr') |
|
| 98 | + ; |
|
| 99 | + } |
|
| 100 | + |
|
| 101 | + /** |
|
| 102 | + * Escapes a string for HTML output. |
|
| 103 | + * @param $string String to escape |
|
| 104 | + */ |
|
| 105 | + protected function escape($string) { |
|
| 106 | + $string = HTMLPurifier_Encoder::cleanUTF8($string); |
|
| 107 | + $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8', false); |
|
| 108 | + return $string; |
|
| 109 | + } |
|
| 110 | + |
|
| 111 | + /** |
|
| 112 | + * Takes a list of strings and turns them into a single list |
|
| 113 | + * @param $array List of strings |
|
| 114 | + * @param $polite Bool whether or not to add an end before the last |
|
| 115 | + */ |
|
| 116 | + protected function listify($array, $polite = false) { |
|
| 117 | + if (empty($array)) return 'None'; |
|
| 118 | + $ret = ''; |
|
| 119 | + $i = count($array); |
|
| 120 | + foreach ($array as $value) { |
|
| 121 | + $i--; |
|
| 122 | + $ret .= $value; |
|
| 123 | + if ($i > 0 && !($polite && $i == 1)) $ret .= ', '; |
|
| 124 | + if ($polite && $i == 1) $ret .= 'and '; |
|
| 125 | + } |
|
| 126 | + return $ret; |
|
| 127 | + } |
|
| 128 | + |
|
| 129 | + /** |
|
| 130 | + * Retrieves the class of an object without prefixes, as well as metadata |
|
| 131 | + * @param $obj Object to determine class of |
|
| 132 | + * @param $prefix Further prefix to remove |
|
| 133 | + */ |
|
| 134 | + protected function getClass($obj, $sec_prefix = '') { |
|
| 135 | + static $five = null; |
|
| 136 | + if ($five === null) $five = version_compare(PHP_VERSION, '5', '>='); |
|
| 137 | + $prefix = 'HTMLPurifier_' . $sec_prefix; |
|
| 138 | + if (!$five) $prefix = strtolower($prefix); |
|
| 139 | + $class = str_replace($prefix, '', get_class($obj)); |
|
| 140 | + $lclass = strtolower($class); |
|
| 141 | + $class .= '('; |
|
| 142 | + switch ($lclass) { |
|
| 143 | + case 'enum': |
|
| 144 | + $values = array(); |
|
| 145 | + foreach ($obj->valid_values as $value => $bool) { |
|
| 146 | + $values[] = $value; |
|
| 147 | + } |
|
| 148 | + $class .= implode(', ', $values); |
|
| 149 | + break; |
|
| 150 | + case 'css_composite': |
|
| 151 | + $values = array(); |
|
| 152 | + foreach ($obj->defs as $def) { |
|
| 153 | + $values[] = $this->getClass($def, $sec_prefix); |
|
| 154 | + } |
|
| 155 | + $class .= implode(', ', $values); |
|
| 156 | + break; |
|
| 157 | + case 'css_multiple': |
|
| 158 | + $class .= $this->getClass($obj->single, $sec_prefix) . ', '; |
|
| 159 | + $class .= $obj->max; |
|
| 160 | + break; |
|
| 161 | + case 'css_denyelementdecorator': |
|
| 162 | + $class .= $this->getClass($obj->def, $sec_prefix) . ', '; |
|
| 163 | + $class .= $obj->element; |
|
| 164 | + break; |
|
| 165 | + case 'css_importantdecorator': |
|
| 166 | + $class .= $this->getClass($obj->def, $sec_prefix); |
|
| 167 | + if ($obj->allow) $class .= ', !important'; |
|
| 168 | + break; |
|
| 169 | + } |
|
| 170 | + $class .= ')'; |
|
| 171 | + return $class; |
|
| 172 | + } |
|
| 173 | 173 | |
| 174 | 174 | } |
| 175 | 175 | |
@@ -89,7 +89,9 @@ discard block |
||
| 89 | 89 | * @param $value Value |
| 90 | 90 | */ |
| 91 | 91 | protected function row($name, $value) { |
| 92 | - if (is_bool($value)) $value = $value ? 'On' : 'Off'; |
|
| 92 | + if (is_bool($value)) { |
|
| 93 | + $value = $value ? 'On' : 'Off'; |
|
| 94 | + } |
|
| 93 | 95 | return |
| 94 | 96 | $this->start('tr') . "\n" . |
| 95 | 97 | $this->element('th', $name) . "\n" . |
@@ -114,14 +116,20 @@ discard block |
||
| 114 | 116 | * @param $polite Bool whether or not to add an end before the last |
| 115 | 117 | */ |
| 116 | 118 | protected function listify($array, $polite = false) { |
| 117 | - if (empty($array)) return 'None'; |
|
| 119 | + if (empty($array)) { |
|
| 120 | + return 'None'; |
|
| 121 | + } |
|
| 118 | 122 | $ret = ''; |
| 119 | 123 | $i = count($array); |
| 120 | 124 | foreach ($array as $value) { |
| 121 | 125 | $i--; |
| 122 | 126 | $ret .= $value; |
| 123 | - if ($i > 0 && !($polite && $i == 1)) $ret .= ', '; |
|
| 124 | - if ($polite && $i == 1) $ret .= 'and '; |
|
| 127 | + if ($i > 0 && !($polite && $i == 1)) { |
|
| 128 | + $ret .= ', '; |
|
| 129 | + } |
|
| 130 | + if ($polite && $i == 1) { |
|
| 131 | + $ret .= 'and '; |
|
| 132 | + } |
|
| 125 | 133 | } |
| 126 | 134 | return $ret; |
| 127 | 135 | } |
@@ -133,9 +141,13 @@ discard block |
||
| 133 | 141 | */ |
| 134 | 142 | protected function getClass($obj, $sec_prefix = '') { |
| 135 | 143 | static $five = null; |
| 136 | - if ($five === null) $five = version_compare(PHP_VERSION, '5', '>='); |
|
| 144 | + if ($five === null) { |
|
| 145 | + $five = version_compare(PHP_VERSION, '5', '>='); |
|
| 146 | + } |
|
| 137 | 147 | $prefix = 'HTMLPurifier_' . $sec_prefix; |
| 138 | - if (!$five) $prefix = strtolower($prefix); |
|
| 148 | + if (!$five) { |
|
| 149 | + $prefix = strtolower($prefix); |
|
| 150 | + } |
|
| 139 | 151 | $class = str_replace($prefix, '', get_class($obj)); |
| 140 | 152 | $lclass = strtolower($class); |
| 141 | 153 | $class .= '('; |
@@ -164,7 +176,9 @@ discard block |
||
| 164 | 176 | break; |
| 165 | 177 | case 'css_importantdecorator': |
| 166 | 178 | $class .= $this->getClass($obj->def, $sec_prefix); |
| 167 | - if ($obj->allow) $class .= ', !important'; |
|
| 179 | + if ($obj->allow) { |
|
| 180 | + $class .= ', !important'; |
|
| 181 | + } |
|
| 168 | 182 | break; |
| 169 | 183 | } |
| 170 | 184 | $class .= ')'; |
@@ -66,8 +66,8 @@ discard block |
||
| 66 | 66 | * @param $escape Bool whether or not to escape contents |
| 67 | 67 | */ |
| 68 | 68 | protected function element($tag, $contents, $attr = array(), $escape = true) { |
| 69 | - return $this->start($tag, $attr) . |
|
| 70 | - ($escape ? $this->escape($contents) : $contents) . |
|
| 69 | + return $this->start($tag, $attr). |
|
| 70 | + ($escape ? $this->escape($contents) : $contents). |
|
| 71 | 71 | $this->end($tag); |
| 72 | 72 | } |
| 73 | 73 | |
@@ -91,9 +91,9 @@ discard block |
||
| 91 | 91 | protected function row($name, $value) { |
| 92 | 92 | if (is_bool($value)) $value = $value ? 'On' : 'Off'; |
| 93 | 93 | return |
| 94 | - $this->start('tr') . "\n" . |
|
| 95 | - $this->element('th', $name) . "\n" . |
|
| 96 | - $this->element('td', $value) . "\n" . |
|
| 94 | + $this->start('tr')."\n". |
|
| 95 | + $this->element('th', $name)."\n". |
|
| 96 | + $this->element('td', $value)."\n". |
|
| 97 | 97 | $this->end('tr') |
| 98 | 98 | ; |
| 99 | 99 | } |
@@ -134,7 +134,7 @@ discard block |
||
| 134 | 134 | protected function getClass($obj, $sec_prefix = '') { |
| 135 | 135 | static $five = null; |
| 136 | 136 | if ($five === null) $five = version_compare(PHP_VERSION, '5', '>='); |
| 137 | - $prefix = 'HTMLPurifier_' . $sec_prefix; |
|
| 137 | + $prefix = 'HTMLPurifier_'.$sec_prefix; |
|
| 138 | 138 | if (!$five) $prefix = strtolower($prefix); |
| 139 | 139 | $class = str_replace($prefix, '', get_class($obj)); |
| 140 | 140 | $lclass = strtolower($class); |
@@ -155,11 +155,11 @@ discard block |
||
| 155 | 155 | $class .= implode(', ', $values); |
| 156 | 156 | break; |
| 157 | 157 | case 'css_multiple': |
| 158 | - $class .= $this->getClass($obj->single, $sec_prefix) . ', '; |
|
| 158 | + $class .= $this->getClass($obj->single, $sec_prefix).', '; |
|
| 159 | 159 | $class .= $obj->max; |
| 160 | 160 | break; |
| 161 | 161 | case 'css_denyelementdecorator': |
| 162 | - $class .= $this->getClass($obj->def, $sec_prefix) . ', '; |
|
| 162 | + $class .= $this->getClass($obj->def, $sec_prefix).', '; |
|
| 163 | 163 | $class .= $obj->element; |
| 164 | 164 | break; |
| 165 | 165 | case 'css_importantdecorator': |
@@ -192,6 +192,7 @@ discard block |
||
| 192 | 192 | |
| 193 | 193 | /** |
| 194 | 194 | * Multiples two numbers, using arbitrary precision when available. |
| 195 | + * @param integer $scale |
|
| 195 | 196 | */ |
| 196 | 197 | private function mul($s1, $s2, $scale) { |
| 197 | 198 | if ($this->bcmath) return bcmul($s1, $s2, $scale); |
@@ -200,6 +201,7 @@ discard block |
||
| 200 | 201 | |
| 201 | 202 | /** |
| 202 | 203 | * Divides two numbers, using arbitrary precision when available. |
| 204 | + * @param integer $scale |
|
| 203 | 205 | */ |
| 204 | 206 | private function div($s1, $s2, $scale) { |
| 205 | 207 | if ($this->bcmath) return bcdiv($s1, $s2, $scale); |
@@ -209,6 +211,7 @@ discard block |
||
| 209 | 211 | /** |
| 210 | 212 | * Rounds a number according to the number of sigfigs it should have, |
| 211 | 213 | * using arbitrary precision when available. |
| 214 | + * @param integer $sigfigs |
|
| 212 | 215 | */ |
| 213 | 216 | private function round($n, $sigfigs) { |
| 214 | 217 | $new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1 |
@@ -7,247 +7,247 @@ |
||
| 7 | 7 | class HTMLPurifier_UnitConverter |
| 8 | 8 | { |
| 9 | 9 | |
| 10 | - const ENGLISH = 1; |
|
| 11 | - const METRIC = 2; |
|
| 12 | - const DIGITAL = 3; |
|
| 13 | - |
|
| 14 | - /** |
|
| 15 | - * Units information array. Units are grouped into measuring systems |
|
| 16 | - * (English, Metric), and are assigned an integer representing |
|
| 17 | - * the conversion factor between that unit and the smallest unit in |
|
| 18 | - * the system. Numeric indexes are actually magical constants that |
|
| 19 | - * encode conversion data from one system to the next, with a O(n^2) |
|
| 20 | - * constraint on memory (this is generally not a problem, since |
|
| 21 | - * the number of measuring systems is small.) |
|
| 22 | - */ |
|
| 23 | - protected static $units = array( |
|
| 24 | - self::ENGLISH => array( |
|
| 25 | - 'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary |
|
| 26 | - 'pt' => 4, |
|
| 27 | - 'pc' => 48, |
|
| 28 | - 'in' => 288, |
|
| 29 | - self::METRIC => array('pt', '0.352777778', 'mm'), |
|
| 30 | - ), |
|
| 31 | - self::METRIC => array( |
|
| 32 | - 'mm' => 1, |
|
| 33 | - 'cm' => 10, |
|
| 34 | - self::ENGLISH => array('mm', '2.83464567', 'pt'), |
|
| 35 | - ), |
|
| 36 | - ); |
|
| 37 | - |
|
| 38 | - /** |
|
| 39 | - * Minimum bcmath precision for output. |
|
| 40 | - */ |
|
| 41 | - protected $outputPrecision; |
|
| 42 | - |
|
| 43 | - /** |
|
| 44 | - * Bcmath precision for internal calculations. |
|
| 45 | - */ |
|
| 46 | - protected $internalPrecision; |
|
| 47 | - |
|
| 48 | - /** |
|
| 49 | - * Whether or not BCMath is available |
|
| 50 | - */ |
|
| 51 | - private $bcmath; |
|
| 52 | - |
|
| 53 | - public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) { |
|
| 54 | - $this->outputPrecision = $output_precision; |
|
| 55 | - $this->internalPrecision = $internal_precision; |
|
| 56 | - $this->bcmath = !$force_no_bcmath && function_exists('bcmul'); |
|
| 57 | - } |
|
| 58 | - |
|
| 59 | - /** |
|
| 60 | - * Converts a length object of one unit into another unit. |
|
| 61 | - * @param HTMLPurifier_Length $length |
|
| 62 | - * Instance of HTMLPurifier_Length to convert. You must validate() |
|
| 63 | - * it before passing it here! |
|
| 64 | - * @param string $to_unit |
|
| 65 | - * Unit to convert to. |
|
| 66 | - * @note |
|
| 67 | - * About precision: This conversion function pays very special |
|
| 68 | - * attention to the incoming precision of values and attempts |
|
| 69 | - * to maintain a number of significant figure. Results are |
|
| 70 | - * fairly accurate up to nine digits. Some caveats: |
|
| 71 | - * - If a number is zero-padded as a result of this significant |
|
| 72 | - * figure tracking, the zeroes will be eliminated. |
|
| 73 | - * - If a number contains less than four sigfigs ($outputPrecision) |
|
| 74 | - * and this causes some decimals to be excluded, those |
|
| 75 | - * decimals will be added on. |
|
| 76 | - */ |
|
| 77 | - public function convert($length, $to_unit) { |
|
| 78 | - |
|
| 79 | - if (!$length->isValid()) return false; |
|
| 80 | - |
|
| 81 | - $n = $length->getN(); |
|
| 82 | - $unit = $length->getUnit(); |
|
| 83 | - |
|
| 84 | - if ($n === '0' || $unit === false) { |
|
| 85 | - return new HTMLPurifier_Length('0', false); |
|
| 86 | - } |
|
| 87 | - |
|
| 88 | - $state = $dest_state = false; |
|
| 89 | - foreach (self::$units as $k => $x) { |
|
| 90 | - if (isset($x[$unit])) $state = $k; |
|
| 91 | - if (isset($x[$to_unit])) $dest_state = $k; |
|
| 92 | - } |
|
| 93 | - if (!$state || !$dest_state) return false; |
|
| 94 | - |
|
| 95 | - // Some calculations about the initial precision of the number; |
|
| 96 | - // this will be useful when we need to do final rounding. |
|
| 97 | - $sigfigs = $this->getSigFigs($n); |
|
| 98 | - if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision; |
|
| 99 | - |
|
| 100 | - // BCMath's internal precision deals only with decimals. Use |
|
| 101 | - // our default if the initial number has no decimals, or increase |
|
| 102 | - // it by how ever many decimals, thus, the number of guard digits |
|
| 103 | - // will always be greater than or equal to internalPrecision. |
|
| 104 | - $log = (int) floor(log(abs($n), 10)); |
|
| 105 | - $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision |
|
| 106 | - |
|
| 107 | - for ($i = 0; $i < 2; $i++) { |
|
| 108 | - |
|
| 109 | - // Determine what unit IN THIS SYSTEM we need to convert to |
|
| 110 | - if ($dest_state === $state) { |
|
| 111 | - // Simple conversion |
|
| 112 | - $dest_unit = $to_unit; |
|
| 113 | - } else { |
|
| 114 | - // Convert to the smallest unit, pending a system shift |
|
| 115 | - $dest_unit = self::$units[$state][$dest_state][0]; |
|
| 116 | - } |
|
| 117 | - |
|
| 118 | - // Do the conversion if necessary |
|
| 119 | - if ($dest_unit !== $unit) { |
|
| 120 | - $factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp); |
|
| 121 | - $n = $this->mul($n, $factor, $cp); |
|
| 122 | - $unit = $dest_unit; |
|
| 123 | - } |
|
| 124 | - |
|
| 125 | - // Output was zero, so bail out early. Shouldn't ever happen. |
|
| 126 | - if ($n === '') { |
|
| 127 | - $n = '0'; |
|
| 128 | - $unit = $to_unit; |
|
| 129 | - break; |
|
| 130 | - } |
|
| 131 | - |
|
| 132 | - // It was a simple conversion, so bail out |
|
| 133 | - if ($dest_state === $state) { |
|
| 134 | - break; |
|
| 135 | - } |
|
| 136 | - |
|
| 137 | - if ($i !== 0) { |
|
| 138 | - // Conversion failed! Apparently, the system we forwarded |
|
| 139 | - // to didn't have this unit. This should never happen! |
|
| 140 | - return false; |
|
| 141 | - } |
|
| 142 | - |
|
| 143 | - // Pre-condition: $i == 0 |
|
| 144 | - |
|
| 145 | - // Perform conversion to next system of units |
|
| 146 | - $n = $this->mul($n, self::$units[$state][$dest_state][1], $cp); |
|
| 147 | - $unit = self::$units[$state][$dest_state][2]; |
|
| 148 | - $state = $dest_state; |
|
| 149 | - |
|
| 150 | - // One more loop around to convert the unit in the new system. |
|
| 151 | - |
|
| 152 | - } |
|
| 153 | - |
|
| 154 | - // Post-condition: $unit == $to_unit |
|
| 155 | - if ($unit !== $to_unit) return false; |
|
| 156 | - |
|
| 157 | - // Useful for debugging: |
|
| 158 | - //echo "<pre>n"; |
|
| 159 | - //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n"; |
|
| 160 | - |
|
| 161 | - $n = $this->round($n, $sigfigs); |
|
| 162 | - if (strpos($n, '.') !== false) $n = rtrim($n, '0'); |
|
| 163 | - $n = rtrim($n, '.'); |
|
| 164 | - |
|
| 165 | - return new HTMLPurifier_Length($n, $unit); |
|
| 166 | - } |
|
| 167 | - |
|
| 168 | - /** |
|
| 169 | - * Returns the number of significant figures in a string number. |
|
| 170 | - * @param string $n Decimal number |
|
| 171 | - * @return int number of sigfigs |
|
| 172 | - */ |
|
| 173 | - public function getSigFigs($n) { |
|
| 174 | - $n = ltrim($n, '0+-'); |
|
| 175 | - $dp = strpos($n, '.'); // decimal position |
|
| 176 | - if ($dp === false) { |
|
| 177 | - $sigfigs = strlen(rtrim($n, '0')); |
|
| 178 | - } else { |
|
| 179 | - $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character |
|
| 180 | - if ($dp !== 0) $sigfigs--; |
|
| 181 | - } |
|
| 182 | - return $sigfigs; |
|
| 183 | - } |
|
| 184 | - |
|
| 185 | - /** |
|
| 186 | - * Adds two numbers, using arbitrary precision when available. |
|
| 187 | - */ |
|
| 188 | - private function add($s1, $s2, $scale) { |
|
| 189 | - if ($this->bcmath) return bcadd($s1, $s2, $scale); |
|
| 190 | - else return $this->scale($s1 + $s2, $scale); |
|
| 191 | - } |
|
| 192 | - |
|
| 193 | - /** |
|
| 194 | - * Multiples two numbers, using arbitrary precision when available. |
|
| 195 | - */ |
|
| 196 | - private function mul($s1, $s2, $scale) { |
|
| 197 | - if ($this->bcmath) return bcmul($s1, $s2, $scale); |
|
| 198 | - else return $this->scale($s1 * $s2, $scale); |
|
| 199 | - } |
|
| 200 | - |
|
| 201 | - /** |
|
| 202 | - * Divides two numbers, using arbitrary precision when available. |
|
| 203 | - */ |
|
| 204 | - private function div($s1, $s2, $scale) { |
|
| 205 | - if ($this->bcmath) return bcdiv($s1, $s2, $scale); |
|
| 206 | - else return $this->scale($s1 / $s2, $scale); |
|
| 207 | - } |
|
| 208 | - |
|
| 209 | - /** |
|
| 210 | - * Rounds a number according to the number of sigfigs it should have, |
|
| 211 | - * using arbitrary precision when available. |
|
| 212 | - */ |
|
| 213 | - private function round($n, $sigfigs) { |
|
| 214 | - $new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1 |
|
| 215 | - $rp = $sigfigs - $new_log - 1; // Number of decimal places needed |
|
| 216 | - $neg = $n < 0 ? '-' : ''; // Negative sign |
|
| 217 | - if ($this->bcmath) { |
|
| 218 | - if ($rp >= 0) { |
|
| 219 | - $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); |
|
| 220 | - $n = bcdiv($n, '1', $rp); |
|
| 221 | - } else { |
|
| 222 | - // This algorithm partially depends on the standardized |
|
| 223 | - // form of numbers that comes out of bcmath. |
|
| 224 | - $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); |
|
| 225 | - $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); |
|
| 226 | - } |
|
| 227 | - return $n; |
|
| 228 | - } else { |
|
| 229 | - return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1); |
|
| 230 | - } |
|
| 231 | - } |
|
| 232 | - |
|
| 233 | - /** |
|
| 234 | - * Scales a float to $scale digits right of decimal point, like BCMath. |
|
| 235 | - */ |
|
| 236 | - private function scale($r, $scale) { |
|
| 237 | - if ($scale < 0) { |
|
| 238 | - // The f sprintf type doesn't support negative numbers, so we |
|
| 239 | - // need to cludge things manually. First get the string. |
|
| 240 | - $r = sprintf('%.0f', (float) $r); |
|
| 241 | - // Due to floating point precision loss, $r will more than likely |
|
| 242 | - // look something like 4652999999999.9234. We grab one more digit |
|
| 243 | - // than we need to precise from $r and then use that to round |
|
| 244 | - // appropriately. |
|
| 245 | - $precise = (string) round(substr($r, 0, strlen($r) + $scale), -1); |
|
| 246 | - // Now we return it, truncating the zero that was rounded off. |
|
| 247 | - return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); |
|
| 248 | - } |
|
| 249 | - return sprintf('%.' . $scale . 'f', (float) $r); |
|
| 250 | - } |
|
| 10 | + const ENGLISH = 1; |
|
| 11 | + const METRIC = 2; |
|
| 12 | + const DIGITAL = 3; |
|
| 13 | + |
|
| 14 | + /** |
|
| 15 | + * Units information array. Units are grouped into measuring systems |
|
| 16 | + * (English, Metric), and are assigned an integer representing |
|
| 17 | + * the conversion factor between that unit and the smallest unit in |
|
| 18 | + * the system. Numeric indexes are actually magical constants that |
|
| 19 | + * encode conversion data from one system to the next, with a O(n^2) |
|
| 20 | + * constraint on memory (this is generally not a problem, since |
|
| 21 | + * the number of measuring systems is small.) |
|
| 22 | + */ |
|
| 23 | + protected static $units = array( |
|
| 24 | + self::ENGLISH => array( |
|
| 25 | + 'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary |
|
| 26 | + 'pt' => 4, |
|
| 27 | + 'pc' => 48, |
|
| 28 | + 'in' => 288, |
|
| 29 | + self::METRIC => array('pt', '0.352777778', 'mm'), |
|
| 30 | + ), |
|
| 31 | + self::METRIC => array( |
|
| 32 | + 'mm' => 1, |
|
| 33 | + 'cm' => 10, |
|
| 34 | + self::ENGLISH => array('mm', '2.83464567', 'pt'), |
|
| 35 | + ), |
|
| 36 | + ); |
|
| 37 | + |
|
| 38 | + /** |
|
| 39 | + * Minimum bcmath precision for output. |
|
| 40 | + */ |
|
| 41 | + protected $outputPrecision; |
|
| 42 | + |
|
| 43 | + /** |
|
| 44 | + * Bcmath precision for internal calculations. |
|
| 45 | + */ |
|
| 46 | + protected $internalPrecision; |
|
| 47 | + |
|
| 48 | + /** |
|
| 49 | + * Whether or not BCMath is available |
|
| 50 | + */ |
|
| 51 | + private $bcmath; |
|
| 52 | + |
|
| 53 | + public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) { |
|
| 54 | + $this->outputPrecision = $output_precision; |
|
| 55 | + $this->internalPrecision = $internal_precision; |
|
| 56 | + $this->bcmath = !$force_no_bcmath && function_exists('bcmul'); |
|
| 57 | + } |
|
| 58 | + |
|
| 59 | + /** |
|
| 60 | + * Converts a length object of one unit into another unit. |
|
| 61 | + * @param HTMLPurifier_Length $length |
|
| 62 | + * Instance of HTMLPurifier_Length to convert. You must validate() |
|
| 63 | + * it before passing it here! |
|
| 64 | + * @param string $to_unit |
|
| 65 | + * Unit to convert to. |
|
| 66 | + * @note |
|
| 67 | + * About precision: This conversion function pays very special |
|
| 68 | + * attention to the incoming precision of values and attempts |
|
| 69 | + * to maintain a number of significant figure. Results are |
|
| 70 | + * fairly accurate up to nine digits. Some caveats: |
|
| 71 | + * - If a number is zero-padded as a result of this significant |
|
| 72 | + * figure tracking, the zeroes will be eliminated. |
|
| 73 | + * - If a number contains less than four sigfigs ($outputPrecision) |
|
| 74 | + * and this causes some decimals to be excluded, those |
|
| 75 | + * decimals will be added on. |
|
| 76 | + */ |
|
| 77 | + public function convert($length, $to_unit) { |
|
| 78 | + |
|
| 79 | + if (!$length->isValid()) return false; |
|
| 80 | + |
|
| 81 | + $n = $length->getN(); |
|
| 82 | + $unit = $length->getUnit(); |
|
| 83 | + |
|
| 84 | + if ($n === '0' || $unit === false) { |
|
| 85 | + return new HTMLPurifier_Length('0', false); |
|
| 86 | + } |
|
| 87 | + |
|
| 88 | + $state = $dest_state = false; |
|
| 89 | + foreach (self::$units as $k => $x) { |
|
| 90 | + if (isset($x[$unit])) $state = $k; |
|
| 91 | + if (isset($x[$to_unit])) $dest_state = $k; |
|
| 92 | + } |
|
| 93 | + if (!$state || !$dest_state) return false; |
|
| 94 | + |
|
| 95 | + // Some calculations about the initial precision of the number; |
|
| 96 | + // this will be useful when we need to do final rounding. |
|
| 97 | + $sigfigs = $this->getSigFigs($n); |
|
| 98 | + if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision; |
|
| 99 | + |
|
| 100 | + // BCMath's internal precision deals only with decimals. Use |
|
| 101 | + // our default if the initial number has no decimals, or increase |
|
| 102 | + // it by how ever many decimals, thus, the number of guard digits |
|
| 103 | + // will always be greater than or equal to internalPrecision. |
|
| 104 | + $log = (int) floor(log(abs($n), 10)); |
|
| 105 | + $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision |
|
| 106 | + |
|
| 107 | + for ($i = 0; $i < 2; $i++) { |
|
| 108 | + |
|
| 109 | + // Determine what unit IN THIS SYSTEM we need to convert to |
|
| 110 | + if ($dest_state === $state) { |
|
| 111 | + // Simple conversion |
|
| 112 | + $dest_unit = $to_unit; |
|
| 113 | + } else { |
|
| 114 | + // Convert to the smallest unit, pending a system shift |
|
| 115 | + $dest_unit = self::$units[$state][$dest_state][0]; |
|
| 116 | + } |
|
| 117 | + |
|
| 118 | + // Do the conversion if necessary |
|
| 119 | + if ($dest_unit !== $unit) { |
|
| 120 | + $factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp); |
|
| 121 | + $n = $this->mul($n, $factor, $cp); |
|
| 122 | + $unit = $dest_unit; |
|
| 123 | + } |
|
| 124 | + |
|
| 125 | + // Output was zero, so bail out early. Shouldn't ever happen. |
|
| 126 | + if ($n === '') { |
|
| 127 | + $n = '0'; |
|
| 128 | + $unit = $to_unit; |
|
| 129 | + break; |
|
| 130 | + } |
|
| 131 | + |
|
| 132 | + // It was a simple conversion, so bail out |
|
| 133 | + if ($dest_state === $state) { |
|
| 134 | + break; |
|
| 135 | + } |
|
| 136 | + |
|
| 137 | + if ($i !== 0) { |
|
| 138 | + // Conversion failed! Apparently, the system we forwarded |
|
| 139 | + // to didn't have this unit. This should never happen! |
|
| 140 | + return false; |
|
| 141 | + } |
|
| 142 | + |
|
| 143 | + // Pre-condition: $i == 0 |
|
| 144 | + |
|
| 145 | + // Perform conversion to next system of units |
|
| 146 | + $n = $this->mul($n, self::$units[$state][$dest_state][1], $cp); |
|
| 147 | + $unit = self::$units[$state][$dest_state][2]; |
|
| 148 | + $state = $dest_state; |
|
| 149 | + |
|
| 150 | + // One more loop around to convert the unit in the new system. |
|
| 151 | + |
|
| 152 | + } |
|
| 153 | + |
|
| 154 | + // Post-condition: $unit == $to_unit |
|
| 155 | + if ($unit !== $to_unit) return false; |
|
| 156 | + |
|
| 157 | + // Useful for debugging: |
|
| 158 | + //echo "<pre>n"; |
|
| 159 | + //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n"; |
|
| 160 | + |
|
| 161 | + $n = $this->round($n, $sigfigs); |
|
| 162 | + if (strpos($n, '.') !== false) $n = rtrim($n, '0'); |
|
| 163 | + $n = rtrim($n, '.'); |
|
| 164 | + |
|
| 165 | + return new HTMLPurifier_Length($n, $unit); |
|
| 166 | + } |
|
| 167 | + |
|
| 168 | + /** |
|
| 169 | + * Returns the number of significant figures in a string number. |
|
| 170 | + * @param string $n Decimal number |
|
| 171 | + * @return int number of sigfigs |
|
| 172 | + */ |
|
| 173 | + public function getSigFigs($n) { |
|
| 174 | + $n = ltrim($n, '0+-'); |
|
| 175 | + $dp = strpos($n, '.'); // decimal position |
|
| 176 | + if ($dp === false) { |
|
| 177 | + $sigfigs = strlen(rtrim($n, '0')); |
|
| 178 | + } else { |
|
| 179 | + $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character |
|
| 180 | + if ($dp !== 0) $sigfigs--; |
|
| 181 | + } |
|
| 182 | + return $sigfigs; |
|
| 183 | + } |
|
| 184 | + |
|
| 185 | + /** |
|
| 186 | + * Adds two numbers, using arbitrary precision when available. |
|
| 187 | + */ |
|
| 188 | + private function add($s1, $s2, $scale) { |
|
| 189 | + if ($this->bcmath) return bcadd($s1, $s2, $scale); |
|
| 190 | + else return $this->scale($s1 + $s2, $scale); |
|
| 191 | + } |
|
| 192 | + |
|
| 193 | + /** |
|
| 194 | + * Multiples two numbers, using arbitrary precision when available. |
|
| 195 | + */ |
|
| 196 | + private function mul($s1, $s2, $scale) { |
|
| 197 | + if ($this->bcmath) return bcmul($s1, $s2, $scale); |
|
| 198 | + else return $this->scale($s1 * $s2, $scale); |
|
| 199 | + } |
|
| 200 | + |
|
| 201 | + /** |
|
| 202 | + * Divides two numbers, using arbitrary precision when available. |
|
| 203 | + */ |
|
| 204 | + private function div($s1, $s2, $scale) { |
|
| 205 | + if ($this->bcmath) return bcdiv($s1, $s2, $scale); |
|
| 206 | + else return $this->scale($s1 / $s2, $scale); |
|
| 207 | + } |
|
| 208 | + |
|
| 209 | + /** |
|
| 210 | + * Rounds a number according to the number of sigfigs it should have, |
|
| 211 | + * using arbitrary precision when available. |
|
| 212 | + */ |
|
| 213 | + private function round($n, $sigfigs) { |
|
| 214 | + $new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1 |
|
| 215 | + $rp = $sigfigs - $new_log - 1; // Number of decimal places needed |
|
| 216 | + $neg = $n < 0 ? '-' : ''; // Negative sign |
|
| 217 | + if ($this->bcmath) { |
|
| 218 | + if ($rp >= 0) { |
|
| 219 | + $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); |
|
| 220 | + $n = bcdiv($n, '1', $rp); |
|
| 221 | + } else { |
|
| 222 | + // This algorithm partially depends on the standardized |
|
| 223 | + // form of numbers that comes out of bcmath. |
|
| 224 | + $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); |
|
| 225 | + $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); |
|
| 226 | + } |
|
| 227 | + return $n; |
|
| 228 | + } else { |
|
| 229 | + return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1); |
|
| 230 | + } |
|
| 231 | + } |
|
| 232 | + |
|
| 233 | + /** |
|
| 234 | + * Scales a float to $scale digits right of decimal point, like BCMath. |
|
| 235 | + */ |
|
| 236 | + private function scale($r, $scale) { |
|
| 237 | + if ($scale < 0) { |
|
| 238 | + // The f sprintf type doesn't support negative numbers, so we |
|
| 239 | + // need to cludge things manually. First get the string. |
|
| 240 | + $r = sprintf('%.0f', (float) $r); |
|
| 241 | + // Due to floating point precision loss, $r will more than likely |
|
| 242 | + // look something like 4652999999999.9234. We grab one more digit |
|
| 243 | + // than we need to precise from $r and then use that to round |
|
| 244 | + // appropriately. |
|
| 245 | + $precise = (string) round(substr($r, 0, strlen($r) + $scale), -1); |
|
| 246 | + // Now we return it, truncating the zero that was rounded off. |
|
| 247 | + return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); |
|
| 248 | + } |
|
| 249 | + return sprintf('%.' . $scale . 'f', (float) $r); |
|
| 250 | + } |
|
| 251 | 251 | |
| 252 | 252 | } |
| 253 | 253 | |
@@ -76,7 +76,9 @@ discard block |
||
| 76 | 76 | */ |
| 77 | 77 | public function convert($length, $to_unit) { |
| 78 | 78 | |
| 79 | - if (!$length->isValid()) return false; |
|
| 79 | + if (!$length->isValid()) { |
|
| 80 | + return false; |
|
| 81 | + } |
|
| 80 | 82 | |
| 81 | 83 | $n = $length->getN(); |
| 82 | 84 | $unit = $length->getUnit(); |
@@ -87,15 +89,23 @@ discard block |
||
| 87 | 89 | |
| 88 | 90 | $state = $dest_state = false; |
| 89 | 91 | foreach (self::$units as $k => $x) { |
| 90 | - if (isset($x[$unit])) $state = $k; |
|
| 91 | - if (isset($x[$to_unit])) $dest_state = $k; |
|
| 92 | + if (isset($x[$unit])) { |
|
| 93 | + $state = $k; |
|
| 94 | + } |
|
| 95 | + if (isset($x[$to_unit])) { |
|
| 96 | + $dest_state = $k; |
|
| 97 | + } |
|
| 98 | + } |
|
| 99 | + if (!$state || !$dest_state) { |
|
| 100 | + return false; |
|
| 92 | 101 | } |
| 93 | - if (!$state || !$dest_state) return false; |
|
| 94 | 102 | |
| 95 | 103 | // Some calculations about the initial precision of the number; |
| 96 | 104 | // this will be useful when we need to do final rounding. |
| 97 | 105 | $sigfigs = $this->getSigFigs($n); |
| 98 | - if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision; |
|
| 106 | + if ($sigfigs < $this->outputPrecision) { |
|
| 107 | + $sigfigs = $this->outputPrecision; |
|
| 108 | + } |
|
| 99 | 109 | |
| 100 | 110 | // BCMath's internal precision deals only with decimals. Use |
| 101 | 111 | // our default if the initial number has no decimals, or increase |
@@ -152,14 +162,18 @@ discard block |
||
| 152 | 162 | } |
| 153 | 163 | |
| 154 | 164 | // Post-condition: $unit == $to_unit |
| 155 | - if ($unit !== $to_unit) return false; |
|
| 165 | + if ($unit !== $to_unit) { |
|
| 166 | + return false; |
|
| 167 | + } |
|
| 156 | 168 | |
| 157 | 169 | // Useful for debugging: |
| 158 | 170 | //echo "<pre>n"; |
| 159 | 171 | //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n"; |
| 160 | 172 | |
| 161 | 173 | $n = $this->round($n, $sigfigs); |
| 162 | - if (strpos($n, '.') !== false) $n = rtrim($n, '0'); |
|
| 174 | + if (strpos($n, '.') !== false) { |
|
| 175 | + $n = rtrim($n, '0'); |
|
| 176 | + } |
|
| 163 | 177 | $n = rtrim($n, '.'); |
| 164 | 178 | |
| 165 | 179 | return new HTMLPurifier_Length($n, $unit); |
@@ -177,7 +191,9 @@ discard block |
||
| 177 | 191 | $sigfigs = strlen(rtrim($n, '0')); |
| 178 | 192 | } else { |
| 179 | 193 | $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character |
| 180 | - if ($dp !== 0) $sigfigs--; |
|
| 194 | + if ($dp !== 0) { |
|
| 195 | + $sigfigs--; |
|
| 196 | + } |
|
| 181 | 197 | } |
| 182 | 198 | return $sigfigs; |
| 183 | 199 | } |
@@ -186,24 +202,33 @@ discard block |
||
| 186 | 202 | * Adds two numbers, using arbitrary precision when available. |
| 187 | 203 | */ |
| 188 | 204 | private function add($s1, $s2, $scale) { |
| 189 | - if ($this->bcmath) return bcadd($s1, $s2, $scale); |
|
| 190 | - else return $this->scale($s1 + $s2, $scale); |
|
| 205 | + if ($this->bcmath) { |
|
| 206 | + return bcadd($s1, $s2, $scale); |
|
| 207 | + } else { |
|
| 208 | + return $this->scale($s1 + $s2, $scale); |
|
| 209 | + } |
|
| 191 | 210 | } |
| 192 | 211 | |
| 193 | 212 | /** |
| 194 | 213 | * Multiples two numbers, using arbitrary precision when available. |
| 195 | 214 | */ |
| 196 | 215 | private function mul($s1, $s2, $scale) { |
| 197 | - if ($this->bcmath) return bcmul($s1, $s2, $scale); |
|
| 198 | - else return $this->scale($s1 * $s2, $scale); |
|
| 216 | + if ($this->bcmath) { |
|
| 217 | + return bcmul($s1, $s2, $scale); |
|
| 218 | + } else { |
|
| 219 | + return $this->scale($s1 * $s2, $scale); |
|
| 220 | + } |
|
| 199 | 221 | } |
| 200 | 222 | |
| 201 | 223 | /** |
| 202 | 224 | * Divides two numbers, using arbitrary precision when available. |
| 203 | 225 | */ |
| 204 | 226 | private function div($s1, $s2, $scale) { |
| 205 | - if ($this->bcmath) return bcdiv($s1, $s2, $scale); |
|
| 206 | - else return $this->scale($s1 / $s2, $scale); |
|
| 227 | + if ($this->bcmath) { |
|
| 228 | + return bcdiv($s1, $s2, $scale); |
|
| 229 | + } else { |
|
| 230 | + return $this->scale($s1 / $s2, $scale); |
|
| 231 | + } |
|
| 207 | 232 | } |
| 208 | 233 | |
| 209 | 234 | /** |
@@ -216,13 +216,13 @@ discard block |
||
| 216 | 216 | $neg = $n < 0 ? '-' : ''; // Negative sign |
| 217 | 217 | if ($this->bcmath) { |
| 218 | 218 | if ($rp >= 0) { |
| 219 | - $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); |
|
| 219 | + $n = bcadd($n, $neg.'0.'.str_repeat('0', $rp).'5', $rp + 1); |
|
| 220 | 220 | $n = bcdiv($n, '1', $rp); |
| 221 | 221 | } else { |
| 222 | 222 | // This algorithm partially depends on the standardized |
| 223 | 223 | // form of numbers that comes out of bcmath. |
| 224 | - $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); |
|
| 225 | - $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); |
|
| 224 | + $n = bcadd($n, $neg.'5'.str_repeat('0', $new_log - $sigfigs), 0); |
|
| 225 | + $n = substr($n, 0, $sigfigs + strlen($neg)).str_repeat('0', $new_log - $sigfigs + 1); |
|
| 226 | 226 | } |
| 227 | 227 | return $n; |
| 228 | 228 | } else { |
@@ -244,9 +244,9 @@ discard block |
||
| 244 | 244 | // appropriately. |
| 245 | 245 | $precise = (string) round(substr($r, 0, strlen($r) + $scale), -1); |
| 246 | 246 | // Now we return it, truncating the zero that was rounded off. |
| 247 | - return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); |
|
| 247 | + return substr($precise, 0, -1).str_repeat('0', -$scale + 1); |
|
| 248 | 248 | } |
| 249 | - return sprintf('%.' . $scale . 'f', (float) $r); |
|
| 249 | + return sprintf('%.'.$scale.'f', (float) $r); |
|
| 250 | 250 | } |
| 251 | 251 | |
| 252 | 252 | } |
@@ -15,6 +15,8 @@ discard block |
||
| 15 | 15 | |
| 16 | 16 | /** |
| 17 | 17 | * @note Automatically normalizes scheme and port |
| 18 | + * @param string|null $host |
|
| 19 | + * @param integer|null $port |
|
| 18 | 20 | */ |
| 19 | 21 | public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) { |
| 20 | 22 | $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme); |
@@ -58,7 +60,7 @@ discard block |
||
| 58 | 60 | * this URI in order to get it into a compliant form. |
| 59 | 61 | * @param $config Instance of HTMLPurifier_Config |
| 60 | 62 | * @param $context Instance of HTMLPurifier_Context |
| 61 | - * @return True if validation/filtering succeeds, false if failure |
|
| 63 | + * @return boolean if validation/filtering succeeds, false if failure |
|
| 62 | 64 | */ |
| 63 | 65 | public function validate($config, $context) { |
| 64 | 66 | |
@@ -11,231 +11,231 @@ |
||
| 11 | 11 | class HTMLPurifier_URI |
| 12 | 12 | { |
| 13 | 13 | |
| 14 | - public $scheme, $userinfo, $host, $port, $path, $query, $fragment; |
|
| 15 | - |
|
| 16 | - /** |
|
| 17 | - * @note Automatically normalizes scheme and port |
|
| 18 | - */ |
|
| 19 | - public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) { |
|
| 20 | - $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme); |
|
| 21 | - $this->userinfo = $userinfo; |
|
| 22 | - $this->host = $host; |
|
| 23 | - $this->port = is_null($port) ? $port : (int) $port; |
|
| 24 | - $this->path = $path; |
|
| 25 | - $this->query = $query; |
|
| 26 | - $this->fragment = $fragment; |
|
| 27 | - } |
|
| 28 | - |
|
| 29 | - /** |
|
| 30 | - * Retrieves a scheme object corresponding to the URI's scheme/default |
|
| 31 | - * @param $config Instance of HTMLPurifier_Config |
|
| 32 | - * @param $context Instance of HTMLPurifier_Context |
|
| 33 | - * @return Scheme object appropriate for validating this URI |
|
| 34 | - */ |
|
| 35 | - public function getSchemeObj($config, $context) { |
|
| 36 | - $registry = HTMLPurifier_URISchemeRegistry::instance(); |
|
| 37 | - if ($this->scheme !== null) { |
|
| 38 | - $scheme_obj = $registry->getScheme($this->scheme, $config, $context); |
|
| 39 | - if (!$scheme_obj) return false; // invalid scheme, clean it out |
|
| 40 | - } else { |
|
| 41 | - // no scheme: retrieve the default one |
|
| 42 | - $def = $config->getDefinition('URI'); |
|
| 43 | - $scheme_obj = $def->getDefaultScheme($config, $context); |
|
| 44 | - if (!$scheme_obj) { |
|
| 45 | - // something funky happened to the default scheme object |
|
| 46 | - trigger_error( |
|
| 47 | - 'Default scheme object "' . $def->defaultScheme . '" was not readable', |
|
| 48 | - E_USER_WARNING |
|
| 49 | - ); |
|
| 50 | - return false; |
|
| 51 | - } |
|
| 52 | - } |
|
| 53 | - return $scheme_obj; |
|
| 54 | - } |
|
| 55 | - |
|
| 56 | - /** |
|
| 57 | - * Generic validation method applicable for all schemes. May modify |
|
| 58 | - * this URI in order to get it into a compliant form. |
|
| 59 | - * @param $config Instance of HTMLPurifier_Config |
|
| 60 | - * @param $context Instance of HTMLPurifier_Context |
|
| 61 | - * @return True if validation/filtering succeeds, false if failure |
|
| 62 | - */ |
|
| 63 | - public function validate($config, $context) { |
|
| 64 | - |
|
| 65 | - // ABNF definitions from RFC 3986 |
|
| 66 | - $chars_sub_delims = '!$&\'()*+,;='; |
|
| 67 | - $chars_gen_delims = ':/?#[]@'; |
|
| 68 | - $chars_pchar = $chars_sub_delims . ':@'; |
|
| 69 | - |
|
| 70 | - // validate host |
|
| 71 | - if (!is_null($this->host)) { |
|
| 72 | - $host_def = new HTMLPurifier_AttrDef_URI_Host(); |
|
| 73 | - $this->host = $host_def->validate($this->host, $config, $context); |
|
| 74 | - if ($this->host === false) $this->host = null; |
|
| 75 | - } |
|
| 76 | - |
|
| 77 | - // validate scheme |
|
| 78 | - // NOTE: It's not appropriate to check whether or not this |
|
| 79 | - // scheme is in our registry, since a URIFilter may convert a |
|
| 80 | - // URI that we don't allow into one we do. So instead, we just |
|
| 81 | - // check if the scheme can be dropped because there is no host |
|
| 82 | - // and it is our default scheme. |
|
| 83 | - if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') { |
|
| 84 | - // support for relative paths is pretty abysmal when the |
|
| 85 | - // scheme is present, so axe it when possible |
|
| 86 | - $def = $config->getDefinition('URI'); |
|
| 87 | - if ($def->defaultScheme === $this->scheme) { |
|
| 88 | - $this->scheme = null; |
|
| 89 | - } |
|
| 90 | - } |
|
| 91 | - |
|
| 92 | - // validate username |
|
| 93 | - if (!is_null($this->userinfo)) { |
|
| 94 | - $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':'); |
|
| 95 | - $this->userinfo = $encoder->encode($this->userinfo); |
|
| 96 | - } |
|
| 97 | - |
|
| 98 | - // validate port |
|
| 99 | - if (!is_null($this->port)) { |
|
| 100 | - if ($this->port < 1 || $this->port > 65535) $this->port = null; |
|
| 101 | - } |
|
| 102 | - |
|
| 103 | - // validate path |
|
| 104 | - $path_parts = array(); |
|
| 105 | - $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/'); |
|
| 106 | - if (!is_null($this->host)) { // this catches $this->host === '' |
|
| 107 | - // path-abempty (hier and relative) |
|
| 108 | - // http://www.example.com/my/path |
|
| 109 | - // //www.example.com/my/path (looks odd, but works, and |
|
| 110 | - // recognized by most browsers) |
|
| 111 | - // (this set is valid or invalid on a scheme by scheme |
|
| 112 | - // basis, so we'll deal with it later) |
|
| 113 | - // file:///my/path |
|
| 114 | - // ///my/path |
|
| 115 | - $this->path = $segments_encoder->encode($this->path); |
|
| 116 | - } elseif ($this->path !== '') { |
|
| 117 | - if ($this->path[0] === '/') { |
|
| 118 | - // path-absolute (hier and relative) |
|
| 119 | - // http:/my/path |
|
| 120 | - // /my/path |
|
| 121 | - if (strlen($this->path) >= 2 && $this->path[1] === '/') { |
|
| 122 | - // This could happen if both the host gets stripped |
|
| 123 | - // out |
|
| 124 | - // http://my/path |
|
| 125 | - // //my/path |
|
| 126 | - $this->path = ''; |
|
| 127 | - } else { |
|
| 128 | - $this->path = $segments_encoder->encode($this->path); |
|
| 129 | - } |
|
| 130 | - } elseif (!is_null($this->scheme)) { |
|
| 131 | - // path-rootless (hier) |
|
| 132 | - // http:my/path |
|
| 133 | - // Short circuit evaluation means we don't need to check nz |
|
| 134 | - $this->path = $segments_encoder->encode($this->path); |
|
| 135 | - } else { |
|
| 136 | - // path-noscheme (relative) |
|
| 137 | - // my/path |
|
| 138 | - // (once again, not checking nz) |
|
| 139 | - $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); |
|
| 140 | - $c = strpos($this->path, '/'); |
|
| 141 | - if ($c !== false) { |
|
| 142 | - $this->path = |
|
| 143 | - $segment_nc_encoder->encode(substr($this->path, 0, $c)) . |
|
| 144 | - $segments_encoder->encode(substr($this->path, $c)); |
|
| 145 | - } else { |
|
| 146 | - $this->path = $segment_nc_encoder->encode($this->path); |
|
| 147 | - } |
|
| 148 | - } |
|
| 149 | - } else { |
|
| 150 | - // path-empty (hier and relative) |
|
| 151 | - $this->path = ''; // just to be safe |
|
| 152 | - } |
|
| 153 | - |
|
| 154 | - // qf = query and fragment |
|
| 155 | - $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?'); |
|
| 156 | - |
|
| 157 | - if (!is_null($this->query)) { |
|
| 158 | - $this->query = $qf_encoder->encode($this->query); |
|
| 159 | - } |
|
| 160 | - |
|
| 161 | - if (!is_null($this->fragment)) { |
|
| 162 | - $this->fragment = $qf_encoder->encode($this->fragment); |
|
| 163 | - } |
|
| 164 | - |
|
| 165 | - return true; |
|
| 166 | - |
|
| 167 | - } |
|
| 168 | - |
|
| 169 | - /** |
|
| 170 | - * Convert URI back to string |
|
| 171 | - * @return String URI appropriate for output |
|
| 172 | - */ |
|
| 173 | - public function toString() { |
|
| 174 | - // reconstruct authority |
|
| 175 | - $authority = null; |
|
| 176 | - // there is a rendering difference between a null authority |
|
| 177 | - // (http:foo-bar) and an empty string authority |
|
| 178 | - // (http:///foo-bar). |
|
| 179 | - if (!is_null($this->host)) { |
|
| 180 | - $authority = ''; |
|
| 181 | - if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@'; |
|
| 182 | - $authority .= $this->host; |
|
| 183 | - if(!is_null($this->port)) $authority .= ':' . $this->port; |
|
| 184 | - } |
|
| 185 | - |
|
| 186 | - // Reconstruct the result |
|
| 187 | - // One might wonder about parsing quirks from browsers after |
|
| 188 | - // this reconstruction. Unfortunately, parsing behavior depends |
|
| 189 | - // on what *scheme* was employed (file:///foo is handled *very* |
|
| 190 | - // differently than http:///foo), so unfortunately we have to |
|
| 191 | - // defer to the schemes to do the right thing. |
|
| 192 | - $result = ''; |
|
| 193 | - if (!is_null($this->scheme)) $result .= $this->scheme . ':'; |
|
| 194 | - if (!is_null($authority)) $result .= '//' . $authority; |
|
| 195 | - $result .= $this->path; |
|
| 196 | - if (!is_null($this->query)) $result .= '?' . $this->query; |
|
| 197 | - if (!is_null($this->fragment)) $result .= '#' . $this->fragment; |
|
| 198 | - |
|
| 199 | - return $result; |
|
| 200 | - } |
|
| 201 | - |
|
| 202 | - /** |
|
| 203 | - * Returns true if this URL might be considered a 'local' URL given |
|
| 204 | - * the current context. This is true when the host is null, or |
|
| 205 | - * when it matches the host supplied to the configuration. |
|
| 206 | - * |
|
| 207 | - * Note that this does not do any scheme checking, so it is mostly |
|
| 208 | - * only appropriate for metadata that doesn't care about protocol |
|
| 209 | - * security. isBenign is probably what you actually want. |
|
| 210 | - */ |
|
| 211 | - public function isLocal($config, $context) { |
|
| 212 | - if ($this->host === null) return true; |
|
| 213 | - $uri_def = $config->getDefinition('URI'); |
|
| 214 | - if ($uri_def->host === $this->host) return true; |
|
| 215 | - return false; |
|
| 216 | - } |
|
| 217 | - |
|
| 218 | - /** |
|
| 219 | - * Returns true if this URL should be considered a 'benign' URL, |
|
| 220 | - * that is: |
|
| 221 | - * |
|
| 222 | - * - It is a local URL (isLocal), and |
|
| 223 | - * - It has a equal or better level of security |
|
| 224 | - */ |
|
| 225 | - public function isBenign($config, $context) { |
|
| 226 | - if (!$this->isLocal($config, $context)) return false; |
|
| 227 | - |
|
| 228 | - $scheme_obj = $this->getSchemeObj($config, $context); |
|
| 229 | - if (!$scheme_obj) return false; // conservative approach |
|
| 230 | - |
|
| 231 | - $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context); |
|
| 232 | - if ($current_scheme_obj->secure) { |
|
| 233 | - if (!$scheme_obj->secure) { |
|
| 234 | - return false; |
|
| 235 | - } |
|
| 236 | - } |
|
| 237 | - return true; |
|
| 238 | - } |
|
| 14 | + public $scheme, $userinfo, $host, $port, $path, $query, $fragment; |
|
| 15 | + |
|
| 16 | + /** |
|
| 17 | + * @note Automatically normalizes scheme and port |
|
| 18 | + */ |
|
| 19 | + public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) { |
|
| 20 | + $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme); |
|
| 21 | + $this->userinfo = $userinfo; |
|
| 22 | + $this->host = $host; |
|
| 23 | + $this->port = is_null($port) ? $port : (int) $port; |
|
| 24 | + $this->path = $path; |
|
| 25 | + $this->query = $query; |
|
| 26 | + $this->fragment = $fragment; |
|
| 27 | + } |
|
| 28 | + |
|
| 29 | + /** |
|
| 30 | + * Retrieves a scheme object corresponding to the URI's scheme/default |
|
| 31 | + * @param $config Instance of HTMLPurifier_Config |
|
| 32 | + * @param $context Instance of HTMLPurifier_Context |
|
| 33 | + * @return Scheme object appropriate for validating this URI |
|
| 34 | + */ |
|
| 35 | + public function getSchemeObj($config, $context) { |
|
| 36 | + $registry = HTMLPurifier_URISchemeRegistry::instance(); |
|
| 37 | + if ($this->scheme !== null) { |
|
| 38 | + $scheme_obj = $registry->getScheme($this->scheme, $config, $context); |
|
| 39 | + if (!$scheme_obj) return false; // invalid scheme, clean it out |
|
| 40 | + } else { |
|
| 41 | + // no scheme: retrieve the default one |
|
| 42 | + $def = $config->getDefinition('URI'); |
|
| 43 | + $scheme_obj = $def->getDefaultScheme($config, $context); |
|
| 44 | + if (!$scheme_obj) { |
|
| 45 | + // something funky happened to the default scheme object |
|
| 46 | + trigger_error( |
|
| 47 | + 'Default scheme object "' . $def->defaultScheme . '" was not readable', |
|
| 48 | + E_USER_WARNING |
|
| 49 | + ); |
|
| 50 | + return false; |
|
| 51 | + } |
|
| 52 | + } |
|
| 53 | + return $scheme_obj; |
|
| 54 | + } |
|
| 55 | + |
|
| 56 | + /** |
|
| 57 | + * Generic validation method applicable for all schemes. May modify |
|
| 58 | + * this URI in order to get it into a compliant form. |
|
| 59 | + * @param $config Instance of HTMLPurifier_Config |
|
| 60 | + * @param $context Instance of HTMLPurifier_Context |
|
| 61 | + * @return True if validation/filtering succeeds, false if failure |
|
| 62 | + */ |
|
| 63 | + public function validate($config, $context) { |
|
| 64 | + |
|
| 65 | + // ABNF definitions from RFC 3986 |
|
| 66 | + $chars_sub_delims = '!$&\'()*+,;='; |
|
| 67 | + $chars_gen_delims = ':/?#[]@'; |
|
| 68 | + $chars_pchar = $chars_sub_delims . ':@'; |
|
| 69 | + |
|
| 70 | + // validate host |
|
| 71 | + if (!is_null($this->host)) { |
|
| 72 | + $host_def = new HTMLPurifier_AttrDef_URI_Host(); |
|
| 73 | + $this->host = $host_def->validate($this->host, $config, $context); |
|
| 74 | + if ($this->host === false) $this->host = null; |
|
| 75 | + } |
|
| 76 | + |
|
| 77 | + // validate scheme |
|
| 78 | + // NOTE: It's not appropriate to check whether or not this |
|
| 79 | + // scheme is in our registry, since a URIFilter may convert a |
|
| 80 | + // URI that we don't allow into one we do. So instead, we just |
|
| 81 | + // check if the scheme can be dropped because there is no host |
|
| 82 | + // and it is our default scheme. |
|
| 83 | + if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') { |
|
| 84 | + // support for relative paths is pretty abysmal when the |
|
| 85 | + // scheme is present, so axe it when possible |
|
| 86 | + $def = $config->getDefinition('URI'); |
|
| 87 | + if ($def->defaultScheme === $this->scheme) { |
|
| 88 | + $this->scheme = null; |
|
| 89 | + } |
|
| 90 | + } |
|
| 91 | + |
|
| 92 | + // validate username |
|
| 93 | + if (!is_null($this->userinfo)) { |
|
| 94 | + $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':'); |
|
| 95 | + $this->userinfo = $encoder->encode($this->userinfo); |
|
| 96 | + } |
|
| 97 | + |
|
| 98 | + // validate port |
|
| 99 | + if (!is_null($this->port)) { |
|
| 100 | + if ($this->port < 1 || $this->port > 65535) $this->port = null; |
|
| 101 | + } |
|
| 102 | + |
|
| 103 | + // validate path |
|
| 104 | + $path_parts = array(); |
|
| 105 | + $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/'); |
|
| 106 | + if (!is_null($this->host)) { // this catches $this->host === '' |
|
| 107 | + // path-abempty (hier and relative) |
|
| 108 | + // http://www.example.com/my/path |
|
| 109 | + // //www.example.com/my/path (looks odd, but works, and |
|
| 110 | + // recognized by most browsers) |
|
| 111 | + // (this set is valid or invalid on a scheme by scheme |
|
| 112 | + // basis, so we'll deal with it later) |
|
| 113 | + // file:///my/path |
|
| 114 | + // ///my/path |
|
| 115 | + $this->path = $segments_encoder->encode($this->path); |
|
| 116 | + } elseif ($this->path !== '') { |
|
| 117 | + if ($this->path[0] === '/') { |
|
| 118 | + // path-absolute (hier and relative) |
|
| 119 | + // http:/my/path |
|
| 120 | + // /my/path |
|
| 121 | + if (strlen($this->path) >= 2 && $this->path[1] === '/') { |
|
| 122 | + // This could happen if both the host gets stripped |
|
| 123 | + // out |
|
| 124 | + // http://my/path |
|
| 125 | + // //my/path |
|
| 126 | + $this->path = ''; |
|
| 127 | + } else { |
|
| 128 | + $this->path = $segments_encoder->encode($this->path); |
|
| 129 | + } |
|
| 130 | + } elseif (!is_null($this->scheme)) { |
|
| 131 | + // path-rootless (hier) |
|
| 132 | + // http:my/path |
|
| 133 | + // Short circuit evaluation means we don't need to check nz |
|
| 134 | + $this->path = $segments_encoder->encode($this->path); |
|
| 135 | + } else { |
|
| 136 | + // path-noscheme (relative) |
|
| 137 | + // my/path |
|
| 138 | + // (once again, not checking nz) |
|
| 139 | + $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); |
|
| 140 | + $c = strpos($this->path, '/'); |
|
| 141 | + if ($c !== false) { |
|
| 142 | + $this->path = |
|
| 143 | + $segment_nc_encoder->encode(substr($this->path, 0, $c)) . |
|
| 144 | + $segments_encoder->encode(substr($this->path, $c)); |
|
| 145 | + } else { |
|
| 146 | + $this->path = $segment_nc_encoder->encode($this->path); |
|
| 147 | + } |
|
| 148 | + } |
|
| 149 | + } else { |
|
| 150 | + // path-empty (hier and relative) |
|
| 151 | + $this->path = ''; // just to be safe |
|
| 152 | + } |
|
| 153 | + |
|
| 154 | + // qf = query and fragment |
|
| 155 | + $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?'); |
|
| 156 | + |
|
| 157 | + if (!is_null($this->query)) { |
|
| 158 | + $this->query = $qf_encoder->encode($this->query); |
|
| 159 | + } |
|
| 160 | + |
|
| 161 | + if (!is_null($this->fragment)) { |
|
| 162 | + $this->fragment = $qf_encoder->encode($this->fragment); |
|
| 163 | + } |
|
| 164 | + |
|
| 165 | + return true; |
|
| 166 | + |
|
| 167 | + } |
|
| 168 | + |
|
| 169 | + /** |
|
| 170 | + * Convert URI back to string |
|
| 171 | + * @return String URI appropriate for output |
|
| 172 | + */ |
|
| 173 | + public function toString() { |
|
| 174 | + // reconstruct authority |
|
| 175 | + $authority = null; |
|
| 176 | + // there is a rendering difference between a null authority |
|
| 177 | + // (http:foo-bar) and an empty string authority |
|
| 178 | + // (http:///foo-bar). |
|
| 179 | + if (!is_null($this->host)) { |
|
| 180 | + $authority = ''; |
|
| 181 | + if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@'; |
|
| 182 | + $authority .= $this->host; |
|
| 183 | + if(!is_null($this->port)) $authority .= ':' . $this->port; |
|
| 184 | + } |
|
| 185 | + |
|
| 186 | + // Reconstruct the result |
|
| 187 | + // One might wonder about parsing quirks from browsers after |
|
| 188 | + // this reconstruction. Unfortunately, parsing behavior depends |
|
| 189 | + // on what *scheme* was employed (file:///foo is handled *very* |
|
| 190 | + // differently than http:///foo), so unfortunately we have to |
|
| 191 | + // defer to the schemes to do the right thing. |
|
| 192 | + $result = ''; |
|
| 193 | + if (!is_null($this->scheme)) $result .= $this->scheme . ':'; |
|
| 194 | + if (!is_null($authority)) $result .= '//' . $authority; |
|
| 195 | + $result .= $this->path; |
|
| 196 | + if (!is_null($this->query)) $result .= '?' . $this->query; |
|
| 197 | + if (!is_null($this->fragment)) $result .= '#' . $this->fragment; |
|
| 198 | + |
|
| 199 | + return $result; |
|
| 200 | + } |
|
| 201 | + |
|
| 202 | + /** |
|
| 203 | + * Returns true if this URL might be considered a 'local' URL given |
|
| 204 | + * the current context. This is true when the host is null, or |
|
| 205 | + * when it matches the host supplied to the configuration. |
|
| 206 | + * |
|
| 207 | + * Note that this does not do any scheme checking, so it is mostly |
|
| 208 | + * only appropriate for metadata that doesn't care about protocol |
|
| 209 | + * security. isBenign is probably what you actually want. |
|
| 210 | + */ |
|
| 211 | + public function isLocal($config, $context) { |
|
| 212 | + if ($this->host === null) return true; |
|
| 213 | + $uri_def = $config->getDefinition('URI'); |
|
| 214 | + if ($uri_def->host === $this->host) return true; |
|
| 215 | + return false; |
|
| 216 | + } |
|
| 217 | + |
|
| 218 | + /** |
|
| 219 | + * Returns true if this URL should be considered a 'benign' URL, |
|
| 220 | + * that is: |
|
| 221 | + * |
|
| 222 | + * - It is a local URL (isLocal), and |
|
| 223 | + * - It has a equal or better level of security |
|
| 224 | + */ |
|
| 225 | + public function isBenign($config, $context) { |
|
| 226 | + if (!$this->isLocal($config, $context)) return false; |
|
| 227 | + |
|
| 228 | + $scheme_obj = $this->getSchemeObj($config, $context); |
|
| 229 | + if (!$scheme_obj) return false; // conservative approach |
|
| 230 | + |
|
| 231 | + $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context); |
|
| 232 | + if ($current_scheme_obj->secure) { |
|
| 233 | + if (!$scheme_obj->secure) { |
|
| 234 | + return false; |
|
| 235 | + } |
|
| 236 | + } |
|
| 237 | + return true; |
|
| 238 | + } |
|
| 239 | 239 | |
| 240 | 240 | } |
| 241 | 241 | |
@@ -36,7 +36,10 @@ discard block |
||
| 36 | 36 | $registry = HTMLPurifier_URISchemeRegistry::instance(); |
| 37 | 37 | if ($this->scheme !== null) { |
| 38 | 38 | $scheme_obj = $registry->getScheme($this->scheme, $config, $context); |
| 39 | - if (!$scheme_obj) return false; // invalid scheme, clean it out |
|
| 39 | + if (!$scheme_obj) { |
|
| 40 | + return false; |
|
| 41 | + } |
|
| 42 | + // invalid scheme, clean it out |
|
| 40 | 43 | } else { |
| 41 | 44 | // no scheme: retrieve the default one |
| 42 | 45 | $def = $config->getDefinition('URI'); |
@@ -71,7 +74,9 @@ discard block |
||
| 71 | 74 | if (!is_null($this->host)) { |
| 72 | 75 | $host_def = new HTMLPurifier_AttrDef_URI_Host(); |
| 73 | 76 | $this->host = $host_def->validate($this->host, $config, $context); |
| 74 | - if ($this->host === false) $this->host = null; |
|
| 77 | + if ($this->host === false) { |
|
| 78 | + $this->host = null; |
|
| 79 | + } |
|
| 75 | 80 | } |
| 76 | 81 | |
| 77 | 82 | // validate scheme |
@@ -97,7 +102,9 @@ discard block |
||
| 97 | 102 | |
| 98 | 103 | // validate port |
| 99 | 104 | if (!is_null($this->port)) { |
| 100 | - if ($this->port < 1 || $this->port > 65535) $this->port = null; |
|
| 105 | + if ($this->port < 1 || $this->port > 65535) { |
|
| 106 | + $this->port = null; |
|
| 107 | + } |
|
| 101 | 108 | } |
| 102 | 109 | |
| 103 | 110 | // validate path |
@@ -178,9 +185,13 @@ discard block |
||
| 178 | 185 | // (http:///foo-bar). |
| 179 | 186 | if (!is_null($this->host)) { |
| 180 | 187 | $authority = ''; |
| 181 | - if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@'; |
|
| 188 | + if(!is_null($this->userinfo)) { |
|
| 189 | + $authority .= $this->userinfo . '@'; |
|
| 190 | + } |
|
| 182 | 191 | $authority .= $this->host; |
| 183 | - if(!is_null($this->port)) $authority .= ':' . $this->port; |
|
| 192 | + if(!is_null($this->port)) { |
|
| 193 | + $authority .= ':' . $this->port; |
|
| 194 | + } |
|
| 184 | 195 | } |
| 185 | 196 | |
| 186 | 197 | // Reconstruct the result |
@@ -190,11 +201,19 @@ discard block |
||
| 190 | 201 | // differently than http:///foo), so unfortunately we have to |
| 191 | 202 | // defer to the schemes to do the right thing. |
| 192 | 203 | $result = ''; |
| 193 | - if (!is_null($this->scheme)) $result .= $this->scheme . ':'; |
|
| 194 | - if (!is_null($authority)) $result .= '//' . $authority; |
|
| 204 | + if (!is_null($this->scheme)) { |
|
| 205 | + $result .= $this->scheme . ':'; |
|
| 206 | + } |
|
| 207 | + if (!is_null($authority)) { |
|
| 208 | + $result .= '//' . $authority; |
|
| 209 | + } |
|
| 195 | 210 | $result .= $this->path; |
| 196 | - if (!is_null($this->query)) $result .= '?' . $this->query; |
|
| 197 | - if (!is_null($this->fragment)) $result .= '#' . $this->fragment; |
|
| 211 | + if (!is_null($this->query)) { |
|
| 212 | + $result .= '?' . $this->query; |
|
| 213 | + } |
|
| 214 | + if (!is_null($this->fragment)) { |
|
| 215 | + $result .= '#' . $this->fragment; |
|
| 216 | + } |
|
| 198 | 217 | |
| 199 | 218 | return $result; |
| 200 | 219 | } |
@@ -209,9 +228,13 @@ discard block |
||
| 209 | 228 | * security. isBenign is probably what you actually want. |
| 210 | 229 | */ |
| 211 | 230 | public function isLocal($config, $context) { |
| 212 | - if ($this->host === null) return true; |
|
| 231 | + if ($this->host === null) { |
|
| 232 | + return true; |
|
| 233 | + } |
|
| 213 | 234 | $uri_def = $config->getDefinition('URI'); |
| 214 | - if ($uri_def->host === $this->host) return true; |
|
| 235 | + if ($uri_def->host === $this->host) { |
|
| 236 | + return true; |
|
| 237 | + } |
|
| 215 | 238 | return false; |
| 216 | 239 | } |
| 217 | 240 | |
@@ -223,10 +246,15 @@ discard block |
||
| 223 | 246 | * - It has a equal or better level of security |
| 224 | 247 | */ |
| 225 | 248 | public function isBenign($config, $context) { |
| 226 | - if (!$this->isLocal($config, $context)) return false; |
|
| 249 | + if (!$this->isLocal($config, $context)) { |
|
| 250 | + return false; |
|
| 251 | + } |
|
| 227 | 252 | |
| 228 | 253 | $scheme_obj = $this->getSchemeObj($config, $context); |
| 229 | - if (!$scheme_obj) return false; // conservative approach |
|
| 254 | + if (!$scheme_obj) { |
|
| 255 | + return false; |
|
| 256 | + } |
|
| 257 | + // conservative approach |
|
| 230 | 258 | |
| 231 | 259 | $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context); |
| 232 | 260 | if ($current_scheme_obj->secure) { |
@@ -44,7 +44,7 @@ discard block |
||
| 44 | 44 | if (!$scheme_obj) { |
| 45 | 45 | // something funky happened to the default scheme object |
| 46 | 46 | trigger_error( |
| 47 | - 'Default scheme object "' . $def->defaultScheme . '" was not readable', |
|
| 47 | + 'Default scheme object "'.$def->defaultScheme.'" was not readable', |
|
| 48 | 48 | E_USER_WARNING |
| 49 | 49 | ); |
| 50 | 50 | return false; |
@@ -65,7 +65,7 @@ discard block |
||
| 65 | 65 | // ABNF definitions from RFC 3986 |
| 66 | 66 | $chars_sub_delims = '!$&\'()*+,;='; |
| 67 | 67 | $chars_gen_delims = ':/?#[]@'; |
| 68 | - $chars_pchar = $chars_sub_delims . ':@'; |
|
| 68 | + $chars_pchar = $chars_sub_delims.':@'; |
|
| 69 | 69 | |
| 70 | 70 | // validate host |
| 71 | 71 | if (!is_null($this->host)) { |
@@ -91,7 +91,7 @@ discard block |
||
| 91 | 91 | |
| 92 | 92 | // validate username |
| 93 | 93 | if (!is_null($this->userinfo)) { |
| 94 | - $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':'); |
|
| 94 | + $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims.':'); |
|
| 95 | 95 | $this->userinfo = $encoder->encode($this->userinfo); |
| 96 | 96 | } |
| 97 | 97 | |
@@ -102,7 +102,7 @@ discard block |
||
| 102 | 102 | |
| 103 | 103 | // validate path |
| 104 | 104 | $path_parts = array(); |
| 105 | - $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/'); |
|
| 105 | + $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar.'/'); |
|
| 106 | 106 | if (!is_null($this->host)) { // this catches $this->host === '' |
| 107 | 107 | // path-abempty (hier and relative) |
| 108 | 108 | // http://www.example.com/my/path |
@@ -136,11 +136,11 @@ discard block |
||
| 136 | 136 | // path-noscheme (relative) |
| 137 | 137 | // my/path |
| 138 | 138 | // (once again, not checking nz) |
| 139 | - $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); |
|
| 139 | + $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims.'@'); |
|
| 140 | 140 | $c = strpos($this->path, '/'); |
| 141 | 141 | if ($c !== false) { |
| 142 | 142 | $this->path = |
| 143 | - $segment_nc_encoder->encode(substr($this->path, 0, $c)) . |
|
| 143 | + $segment_nc_encoder->encode(substr($this->path, 0, $c)). |
|
| 144 | 144 | $segments_encoder->encode(substr($this->path, $c)); |
| 145 | 145 | } else { |
| 146 | 146 | $this->path = $segment_nc_encoder->encode($this->path); |
@@ -152,7 +152,7 @@ discard block |
||
| 152 | 152 | } |
| 153 | 153 | |
| 154 | 154 | // qf = query and fragment |
| 155 | - $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?'); |
|
| 155 | + $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar.'/?'); |
|
| 156 | 156 | |
| 157 | 157 | if (!is_null($this->query)) { |
| 158 | 158 | $this->query = $qf_encoder->encode($this->query); |
@@ -178,9 +178,9 @@ discard block |
||
| 178 | 178 | // (http:///foo-bar). |
| 179 | 179 | if (!is_null($this->host)) { |
| 180 | 180 | $authority = ''; |
| 181 | - if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@'; |
|
| 181 | + if (!is_null($this->userinfo)) $authority .= $this->userinfo.'@'; |
|
| 182 | 182 | $authority .= $this->host; |
| 183 | - if(!is_null($this->port)) $authority .= ':' . $this->port; |
|
| 183 | + if (!is_null($this->port)) $authority .= ':'.$this->port; |
|
| 184 | 184 | } |
| 185 | 185 | |
| 186 | 186 | // Reconstruct the result |
@@ -190,11 +190,11 @@ discard block |
||
| 190 | 190 | // differently than http:///foo), so unfortunately we have to |
| 191 | 191 | // defer to the schemes to do the right thing. |
| 192 | 192 | $result = ''; |
| 193 | - if (!is_null($this->scheme)) $result .= $this->scheme . ':'; |
|
| 194 | - if (!is_null($authority)) $result .= '//' . $authority; |
|
| 193 | + if (!is_null($this->scheme)) $result .= $this->scheme.':'; |
|
| 194 | + if (!is_null($authority)) $result .= '//'.$authority; |
|
| 195 | 195 | $result .= $this->path; |
| 196 | - if (!is_null($this->query)) $result .= '?' . $this->query; |
|
| 197 | - if (!is_null($this->fragment)) $result .= '#' . $this->fragment; |
|
| 196 | + if (!is_null($this->query)) $result .= '?'.$this->query; |
|
| 197 | + if (!is_null($this->fragment)) $result .= '#'.$this->fragment; |
|
| 198 | 198 | |
| 199 | 199 | return $result; |
| 200 | 200 | } |
@@ -109,6 +109,7 @@ discard block |
||
| 109 | 109 | /** |
| 110 | 110 | * Actually implements the parsing. Base implementation is to not |
| 111 | 111 | * do anything to $var. Subclasses should overload this! |
| 112 | + * @param boolean $allow_null |
|
| 112 | 113 | */ |
| 113 | 114 | protected function parseImplementation($var, $type, $allow_null) { |
| 114 | 115 | return $var; |
@@ -116,6 +117,7 @@ discard block |
||
| 116 | 117 | |
| 117 | 118 | /** |
| 118 | 119 | * Throws an exception. |
| 120 | + * @param string $msg |
|
| 119 | 121 | */ |
| 120 | 122 | protected function error($msg) { |
| 121 | 123 | throw new HTMLPurifier_VarParserException($msg); |
@@ -126,6 +128,7 @@ discard block |
||
| 126 | 128 | * @note This should not ever be called. It would be called if we |
| 127 | 129 | * extend the allowed values of HTMLPurifier_VarParser without |
| 128 | 130 | * updating subclasses. |
| 131 | + * @param string $class |
|
| 129 | 132 | */ |
| 130 | 133 | protected function errorInconsistent($class, $type) { |
| 131 | 134 | throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented"); |
@@ -7,147 +7,147 @@ |
||
| 7 | 7 | class HTMLPurifier_VarParser |
| 8 | 8 | { |
| 9 | 9 | |
| 10 | - const STRING = 1; |
|
| 11 | - const ISTRING = 2; |
|
| 12 | - const TEXT = 3; |
|
| 13 | - const ITEXT = 4; |
|
| 14 | - const INT = 5; |
|
| 15 | - const FLOAT = 6; |
|
| 16 | - const BOOL = 7; |
|
| 17 | - const LOOKUP = 8; |
|
| 18 | - const ALIST = 9; |
|
| 19 | - const HASH = 10; |
|
| 20 | - const MIXED = 11; |
|
| 10 | + const STRING = 1; |
|
| 11 | + const ISTRING = 2; |
|
| 12 | + const TEXT = 3; |
|
| 13 | + const ITEXT = 4; |
|
| 14 | + const INT = 5; |
|
| 15 | + const FLOAT = 6; |
|
| 16 | + const BOOL = 7; |
|
| 17 | + const LOOKUP = 8; |
|
| 18 | + const ALIST = 9; |
|
| 19 | + const HASH = 10; |
|
| 20 | + const MIXED = 11; |
|
| 21 | 21 | |
| 22 | - /** |
|
| 23 | - * Lookup table of allowed types. Mainly for backwards compatibility, but |
|
| 24 | - * also convenient for transforming string type names to the integer constants. |
|
| 25 | - */ |
|
| 26 | - static public $types = array( |
|
| 27 | - 'string' => self::STRING, |
|
| 28 | - 'istring' => self::ISTRING, |
|
| 29 | - 'text' => self::TEXT, |
|
| 30 | - 'itext' => self::ITEXT, |
|
| 31 | - 'int' => self::INT, |
|
| 32 | - 'float' => self::FLOAT, |
|
| 33 | - 'bool' => self::BOOL, |
|
| 34 | - 'lookup' => self::LOOKUP, |
|
| 35 | - 'list' => self::ALIST, |
|
| 36 | - 'hash' => self::HASH, |
|
| 37 | - 'mixed' => self::MIXED |
|
| 38 | - ); |
|
| 22 | + /** |
|
| 23 | + * Lookup table of allowed types. Mainly for backwards compatibility, but |
|
| 24 | + * also convenient for transforming string type names to the integer constants. |
|
| 25 | + */ |
|
| 26 | + static public $types = array( |
|
| 27 | + 'string' => self::STRING, |
|
| 28 | + 'istring' => self::ISTRING, |
|
| 29 | + 'text' => self::TEXT, |
|
| 30 | + 'itext' => self::ITEXT, |
|
| 31 | + 'int' => self::INT, |
|
| 32 | + 'float' => self::FLOAT, |
|
| 33 | + 'bool' => self::BOOL, |
|
| 34 | + 'lookup' => self::LOOKUP, |
|
| 35 | + 'list' => self::ALIST, |
|
| 36 | + 'hash' => self::HASH, |
|
| 37 | + 'mixed' => self::MIXED |
|
| 38 | + ); |
|
| 39 | 39 | |
| 40 | - /** |
|
| 41 | - * Lookup table of types that are string, and can have aliases or |
|
| 42 | - * allowed value lists. |
|
| 43 | - */ |
|
| 44 | - static public $stringTypes = array( |
|
| 45 | - self::STRING => true, |
|
| 46 | - self::ISTRING => true, |
|
| 47 | - self::TEXT => true, |
|
| 48 | - self::ITEXT => true, |
|
| 49 | - ); |
|
| 40 | + /** |
|
| 41 | + * Lookup table of types that are string, and can have aliases or |
|
| 42 | + * allowed value lists. |
|
| 43 | + */ |
|
| 44 | + static public $stringTypes = array( |
|
| 45 | + self::STRING => true, |
|
| 46 | + self::ISTRING => true, |
|
| 47 | + self::TEXT => true, |
|
| 48 | + self::ITEXT => true, |
|
| 49 | + ); |
|
| 50 | 50 | |
| 51 | - /** |
|
| 52 | - * Validate a variable according to type. Throws |
|
| 53 | - * HTMLPurifier_VarParserException if invalid. |
|
| 54 | - * It may return NULL as a valid type if $allow_null is true. |
|
| 55 | - * |
|
| 56 | - * @param $var Variable to validate |
|
| 57 | - * @param $type Type of variable, see HTMLPurifier_VarParser->types |
|
| 58 | - * @param $allow_null Whether or not to permit null as a value |
|
| 59 | - * @return Validated and type-coerced variable |
|
| 60 | - */ |
|
| 61 | - final public function parse($var, $type, $allow_null = false) { |
|
| 62 | - if (is_string($type)) { |
|
| 63 | - if (!isset(HTMLPurifier_VarParser::$types[$type])) { |
|
| 64 | - throw new HTMLPurifier_VarParserException("Invalid type '$type'"); |
|
| 65 | - } else { |
|
| 66 | - $type = HTMLPurifier_VarParser::$types[$type]; |
|
| 67 | - } |
|
| 68 | - } |
|
| 69 | - $var = $this->parseImplementation($var, $type, $allow_null); |
|
| 70 | - if ($allow_null && $var === null) return null; |
|
| 71 | - // These are basic checks, to make sure nothing horribly wrong |
|
| 72 | - // happened in our implementations. |
|
| 73 | - switch ($type) { |
|
| 74 | - case (self::STRING): |
|
| 75 | - case (self::ISTRING): |
|
| 76 | - case (self::TEXT): |
|
| 77 | - case (self::ITEXT): |
|
| 78 | - if (!is_string($var)) break; |
|
| 79 | - if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var); |
|
| 80 | - return $var; |
|
| 81 | - case (self::INT): |
|
| 82 | - if (!is_int($var)) break; |
|
| 83 | - return $var; |
|
| 84 | - case (self::FLOAT): |
|
| 85 | - if (!is_float($var)) break; |
|
| 86 | - return $var; |
|
| 87 | - case (self::BOOL): |
|
| 88 | - if (!is_bool($var)) break; |
|
| 89 | - return $var; |
|
| 90 | - case (self::LOOKUP): |
|
| 91 | - case (self::ALIST): |
|
| 92 | - case (self::HASH): |
|
| 93 | - if (!is_array($var)) break; |
|
| 94 | - if ($type === self::LOOKUP) { |
|
| 95 | - foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true'); |
|
| 96 | - } elseif ($type === self::ALIST) { |
|
| 97 | - $keys = array_keys($var); |
|
| 98 | - if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform'); |
|
| 99 | - } |
|
| 100 | - return $var; |
|
| 101 | - case (self::MIXED): |
|
| 102 | - return $var; |
|
| 103 | - default: |
|
| 104 | - $this->errorInconsistent(get_class($this), $type); |
|
| 105 | - } |
|
| 106 | - $this->errorGeneric($var, $type); |
|
| 107 | - } |
|
| 51 | + /** |
|
| 52 | + * Validate a variable according to type. Throws |
|
| 53 | + * HTMLPurifier_VarParserException if invalid. |
|
| 54 | + * It may return NULL as a valid type if $allow_null is true. |
|
| 55 | + * |
|
| 56 | + * @param $var Variable to validate |
|
| 57 | + * @param $type Type of variable, see HTMLPurifier_VarParser->types |
|
| 58 | + * @param $allow_null Whether or not to permit null as a value |
|
| 59 | + * @return Validated and type-coerced variable |
|
| 60 | + */ |
|
| 61 | + final public function parse($var, $type, $allow_null = false) { |
|
| 62 | + if (is_string($type)) { |
|
| 63 | + if (!isset(HTMLPurifier_VarParser::$types[$type])) { |
|
| 64 | + throw new HTMLPurifier_VarParserException("Invalid type '$type'"); |
|
| 65 | + } else { |
|
| 66 | + $type = HTMLPurifier_VarParser::$types[$type]; |
|
| 67 | + } |
|
| 68 | + } |
|
| 69 | + $var = $this->parseImplementation($var, $type, $allow_null); |
|
| 70 | + if ($allow_null && $var === null) return null; |
|
| 71 | + // These are basic checks, to make sure nothing horribly wrong |
|
| 72 | + // happened in our implementations. |
|
| 73 | + switch ($type) { |
|
| 74 | + case (self::STRING): |
|
| 75 | + case (self::ISTRING): |
|
| 76 | + case (self::TEXT): |
|
| 77 | + case (self::ITEXT): |
|
| 78 | + if (!is_string($var)) break; |
|
| 79 | + if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var); |
|
| 80 | + return $var; |
|
| 81 | + case (self::INT): |
|
| 82 | + if (!is_int($var)) break; |
|
| 83 | + return $var; |
|
| 84 | + case (self::FLOAT): |
|
| 85 | + if (!is_float($var)) break; |
|
| 86 | + return $var; |
|
| 87 | + case (self::BOOL): |
|
| 88 | + if (!is_bool($var)) break; |
|
| 89 | + return $var; |
|
| 90 | + case (self::LOOKUP): |
|
| 91 | + case (self::ALIST): |
|
| 92 | + case (self::HASH): |
|
| 93 | + if (!is_array($var)) break; |
|
| 94 | + if ($type === self::LOOKUP) { |
|
| 95 | + foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true'); |
|
| 96 | + } elseif ($type === self::ALIST) { |
|
| 97 | + $keys = array_keys($var); |
|
| 98 | + if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform'); |
|
| 99 | + } |
|
| 100 | + return $var; |
|
| 101 | + case (self::MIXED): |
|
| 102 | + return $var; |
|
| 103 | + default: |
|
| 104 | + $this->errorInconsistent(get_class($this), $type); |
|
| 105 | + } |
|
| 106 | + $this->errorGeneric($var, $type); |
|
| 107 | + } |
|
| 108 | 108 | |
| 109 | - /** |
|
| 110 | - * Actually implements the parsing. Base implementation is to not |
|
| 111 | - * do anything to $var. Subclasses should overload this! |
|
| 112 | - */ |
|
| 113 | - protected function parseImplementation($var, $type, $allow_null) { |
|
| 114 | - return $var; |
|
| 115 | - } |
|
| 109 | + /** |
|
| 110 | + * Actually implements the parsing. Base implementation is to not |
|
| 111 | + * do anything to $var. Subclasses should overload this! |
|
| 112 | + */ |
|
| 113 | + protected function parseImplementation($var, $type, $allow_null) { |
|
| 114 | + return $var; |
|
| 115 | + } |
|
| 116 | 116 | |
| 117 | - /** |
|
| 118 | - * Throws an exception. |
|
| 119 | - */ |
|
| 120 | - protected function error($msg) { |
|
| 121 | - throw new HTMLPurifier_VarParserException($msg); |
|
| 122 | - } |
|
| 117 | + /** |
|
| 118 | + * Throws an exception. |
|
| 119 | + */ |
|
| 120 | + protected function error($msg) { |
|
| 121 | + throw new HTMLPurifier_VarParserException($msg); |
|
| 122 | + } |
|
| 123 | 123 | |
| 124 | - /** |
|
| 125 | - * Throws an inconsistency exception. |
|
| 126 | - * @note This should not ever be called. It would be called if we |
|
| 127 | - * extend the allowed values of HTMLPurifier_VarParser without |
|
| 128 | - * updating subclasses. |
|
| 129 | - */ |
|
| 130 | - protected function errorInconsistent($class, $type) { |
|
| 131 | - throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented"); |
|
| 132 | - } |
|
| 124 | + /** |
|
| 125 | + * Throws an inconsistency exception. |
|
| 126 | + * @note This should not ever be called. It would be called if we |
|
| 127 | + * extend the allowed values of HTMLPurifier_VarParser without |
|
| 128 | + * updating subclasses. |
|
| 129 | + */ |
|
| 130 | + protected function errorInconsistent($class, $type) { |
|
| 131 | + throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented"); |
|
| 132 | + } |
|
| 133 | 133 | |
| 134 | - /** |
|
| 135 | - * Generic error for if a type didn't work. |
|
| 136 | - */ |
|
| 137 | - protected function errorGeneric($var, $type) { |
|
| 138 | - $vtype = gettype($var); |
|
| 139 | - $this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype"); |
|
| 140 | - } |
|
| 134 | + /** |
|
| 135 | + * Generic error for if a type didn't work. |
|
| 136 | + */ |
|
| 137 | + protected function errorGeneric($var, $type) { |
|
| 138 | + $vtype = gettype($var); |
|
| 139 | + $this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype"); |
|
| 140 | + } |
|
| 141 | 141 | |
| 142 | - static public function getTypeName($type) { |
|
| 143 | - static $lookup; |
|
| 144 | - if (!$lookup) { |
|
| 145 | - // Lazy load the alternative lookup table |
|
| 146 | - $lookup = array_flip(HTMLPurifier_VarParser::$types); |
|
| 147 | - } |
|
| 148 | - if (!isset($lookup[$type])) return 'unknown'; |
|
| 149 | - return $lookup[$type]; |
|
| 150 | - } |
|
| 142 | + static public function getTypeName($type) { |
|
| 143 | + static $lookup; |
|
| 144 | + if (!$lookup) { |
|
| 145 | + // Lazy load the alternative lookup table |
|
| 146 | + $lookup = array_flip(HTMLPurifier_VarParser::$types); |
|
| 147 | + } |
|
| 148 | + if (!isset($lookup[$type])) return 'unknown'; |
|
| 149 | + return $lookup[$type]; |
|
| 150 | + } |
|
| 151 | 151 | |
| 152 | 152 | } |
| 153 | 153 | |
@@ -67,7 +67,9 @@ discard block |
||
| 67 | 67 | } |
| 68 | 68 | } |
| 69 | 69 | $var = $this->parseImplementation($var, $type, $allow_null); |
| 70 | - if ($allow_null && $var === null) return null; |
|
| 70 | + if ($allow_null && $var === null) { |
|
| 71 | + return null; |
|
| 72 | + } |
|
| 71 | 73 | // These are basic checks, to make sure nothing horribly wrong |
| 72 | 74 | // happened in our implementations. |
| 73 | 75 | switch ($type) { |
@@ -75,27 +77,43 @@ discard block |
||
| 75 | 77 | case (self::ISTRING): |
| 76 | 78 | case (self::TEXT): |
| 77 | 79 | case (self::ITEXT): |
| 78 | - if (!is_string($var)) break; |
|
| 79 | - if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var); |
|
| 80 | + if (!is_string($var)) { |
|
| 81 | + break; |
|
| 82 | + } |
|
| 83 | + if ($type == self::ISTRING || $type == self::ITEXT) { |
|
| 84 | + $var = strtolower($var); |
|
| 85 | + } |
|
| 80 | 86 | return $var; |
| 81 | 87 | case (self::INT): |
| 82 | - if (!is_int($var)) break; |
|
| 88 | + if (!is_int($var)) { |
|
| 89 | + break; |
|
| 90 | + } |
|
| 83 | 91 | return $var; |
| 84 | 92 | case (self::FLOAT): |
| 85 | - if (!is_float($var)) break; |
|
| 93 | + if (!is_float($var)) { |
|
| 94 | + break; |
|
| 95 | + } |
|
| 86 | 96 | return $var; |
| 87 | 97 | case (self::BOOL): |
| 88 | - if (!is_bool($var)) break; |
|
| 98 | + if (!is_bool($var)) { |
|
| 99 | + break; |
|
| 100 | + } |
|
| 89 | 101 | return $var; |
| 90 | 102 | case (self::LOOKUP): |
| 91 | 103 | case (self::ALIST): |
| 92 | 104 | case (self::HASH): |
| 93 | - if (!is_array($var)) break; |
|
| 105 | + if (!is_array($var)) { |
|
| 106 | + break; |
|
| 107 | + } |
|
| 94 | 108 | if ($type === self::LOOKUP) { |
| 95 | - foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true'); |
|
| 109 | + foreach ($var as $k) { |
|
| 110 | + if ($k !== true) $this->error('Lookup table contains value other than true'); |
|
| 111 | + } |
|
| 96 | 112 | } elseif ($type === self::ALIST) { |
| 97 | 113 | $keys = array_keys($var); |
| 98 | - if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform'); |
|
| 114 | + if (array_keys($keys) !== $keys) { |
|
| 115 | + $this->error('Indices for list are not uniform'); |
|
| 116 | + } |
|
| 99 | 117 | } |
| 100 | 118 | return $var; |
| 101 | 119 | case (self::MIXED): |
@@ -145,7 +163,9 @@ discard block |
||
| 145 | 163 | // Lazy load the alternative lookup table |
| 146 | 164 | $lookup = array_flip(HTMLPurifier_VarParser::$types); |
| 147 | 165 | } |
| 148 | - if (!isset($lookup[$type])) return 'unknown'; |
|
| 166 | + if (!isset($lookup[$type])) { |
|
| 167 | + return 'unknown'; |
|
| 168 | + } |
|
| 149 | 169 | return $lookup[$type]; |
| 150 | 170 | } |
| 151 | 171 | |
@@ -5,6 +5,9 @@ |
||
| 5 | 5 | { |
| 6 | 6 | private static $_block_list = array ('exec', 'system', 'passthru', 'show_source', 'phpinfo', 'fopen', 'file_get_contents', 'file_put_contents', 'fwrite', 'proc_open', 'popen'); |
| 7 | 7 | |
| 8 | + /** |
|
| 9 | + * @param string $file |
|
| 10 | + */ |
|
| 8 | 11 | public function check($file) |
| 9 | 12 | { |
| 10 | 13 | // TODO: 기능개선후 enable |
@@ -3,38 +3,38 @@ |
||
| 3 | 3 | |
| 4 | 4 | class UploadFileFilter |
| 5 | 5 | { |
| 6 | - private static $_block_list = array ('exec', 'system', 'passthru', 'show_source', 'phpinfo', 'fopen', 'file_get_contents', 'file_put_contents', 'fwrite', 'proc_open', 'popen'); |
|
| 6 | + private static $_block_list = array('exec', 'system', 'passthru', 'show_source', 'phpinfo', 'fopen', 'file_get_contents', 'file_put_contents', 'fwrite', 'proc_open', 'popen'); |
|
| 7 | 7 | |
| 8 | 8 | public function check($file) |
| 9 | 9 | { |
| 10 | 10 | // TODO: 기능개선후 enable |
| 11 | 11 | |
| 12 | 12 | return TRUE; // disable |
| 13 | - if (! $file || ! FileHandler::exists($file)) return TRUE; |
|
| 14 | - return self::_check ( $file ); |
|
| 13 | + if (!$file || !FileHandler::exists($file)) return TRUE; |
|
| 14 | + return self::_check($file); |
|
| 15 | 15 | } |
| 16 | 16 | |
| 17 | 17 | private function _check($file) |
| 18 | 18 | { |
| 19 | - if (! ($fp = fopen ( $file, 'r' ))) return FALSE; |
|
| 19 | + if (!($fp = fopen($file, 'r'))) return FALSE; |
|
| 20 | 20 | |
| 21 | 21 | $has_php_tag = FALSE; |
| 22 | 22 | |
| 23 | - while ( ! feof ( $fp ) ) |
|
| 23 | + while (!feof($fp)) |
|
| 24 | 24 | { |
| 25 | - $content = fread ( $fp, 8192 ); |
|
| 26 | - if (FALSE === $has_php_tag) $has_php_tag = strpos ( $content, '<?' ); |
|
| 27 | - foreach ( self::$_block_list as $v ) |
|
| 25 | + $content = fread($fp, 8192); |
|
| 26 | + if (FALSE === $has_php_tag) $has_php_tag = strpos($content, '<?'); |
|
| 27 | + foreach (self::$_block_list as $v) |
|
| 28 | 28 | { |
| 29 | - if (FALSE !== $has_php_tag && FALSE !== strpos ( $content, $v )) |
|
| 29 | + if (FALSE !== $has_php_tag && FALSE !== strpos($content, $v)) |
|
| 30 | 30 | { |
| 31 | - fclose ( $fp ); |
|
| 31 | + fclose($fp); |
|
| 32 | 32 | return FALSE; |
| 33 | 33 | } |
| 34 | 34 | } |
| 35 | 35 | } |
| 36 | 36 | |
| 37 | - fclose ( $fp ); |
|
| 37 | + fclose($fp); |
|
| 38 | 38 | |
| 39 | 39 | return TRUE; |
| 40 | 40 | } |
@@ -10,20 +10,26 @@ |
||
| 10 | 10 | // TODO: 기능개선후 enable |
| 11 | 11 | |
| 12 | 12 | return TRUE; // disable |
| 13 | - if (! $file || ! FileHandler::exists($file)) return TRUE; |
|
| 13 | + if (! $file || ! FileHandler::exists($file)) { |
|
| 14 | + return TRUE; |
|
| 15 | + } |
|
| 14 | 16 | return self::_check ( $file ); |
| 15 | 17 | } |
| 16 | 18 | |
| 17 | 19 | private function _check($file) |
| 18 | 20 | { |
| 19 | - if (! ($fp = fopen ( $file, 'r' ))) return FALSE; |
|
| 21 | + if (! ($fp = fopen ( $file, 'r' ))) { |
|
| 22 | + return FALSE; |
|
| 23 | + } |
|
| 20 | 24 | |
| 21 | 25 | $has_php_tag = FALSE; |
| 22 | 26 | |
| 23 | 27 | while ( ! feof ( $fp ) ) |
| 24 | 28 | { |
| 25 | 29 | $content = fread ( $fp, 8192 ); |
| 26 | - if (FALSE === $has_php_tag) $has_php_tag = strpos ( $content, '<?' ); |
|
| 30 | + if (FALSE === $has_php_tag) { |
|
| 31 | + $has_php_tag = strpos ( $content, '<?' ); |
|
| 32 | + } |
|
| 27 | 33 | foreach ( self::$_block_list as $v ) |
| 28 | 34 | { |
| 29 | 35 | if (FALSE !== $has_php_tag && FALSE !== strpos ( $content, $v )) |
@@ -25,7 +25,7 @@ |
||
| 25 | 25 | |
| 26 | 26 | /** |
| 27 | 27 | * constructor |
| 28 | - * @return void |
|
| 28 | + * @return string |
|
| 29 | 29 | */ |
| 30 | 30 | public function __construct() |
| 31 | 31 | { |
@@ -376,7 +376,7 @@ discard block |
||
| 376 | 376 | //parse error |
| 377 | 377 | if ($error_info['type'] == 4) |
| 378 | 378 | { |
| 379 | - throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}"); |
|
| 379 | + throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}"); |
|
| 380 | 380 | } |
| 381 | 381 | } |
| 382 | 382 | else |
@@ -392,7 +392,7 @@ discard block |
||
| 392 | 392 | //parse error |
| 393 | 393 | if ($error_info['type'] == 4) |
| 394 | 394 | { |
| 395 | - throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}"); |
|
| 395 | + throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}"); |
|
| 396 | 396 | } |
| 397 | 397 | } |
| 398 | 398 | |
@@ -46,8 +46,7 @@ discard block |
||
| 46 | 46 | if(!isset($GLOBALS['__TemplateHandlerCalled__'])) |
| 47 | 47 | { |
| 48 | 48 | $GLOBALS['__TemplateHandlerCalled__'] = 1; |
| 49 | - } |
|
| 50 | - else |
|
| 49 | + } else |
|
| 51 | 50 | { |
| 52 | 51 | $GLOBALS['__TemplateHandlerCalled__']++; |
| 53 | 52 | } |
@@ -150,8 +149,7 @@ discard block |
||
| 150 | 149 | { |
| 151 | 150 | $cache_key = 'template:' . $this->file; |
| 152 | 151 | $buff = $oCacheHandler->get($cache_key, $latest_mtime); |
| 153 | - } |
|
| 154 | - else |
|
| 152 | + } else |
|
| 155 | 153 | { |
| 156 | 154 | if(is_readable($this->compiled_file) && filemtime($this->compiled_file) > $latest_mtime && filesize($this->compiled_file)) |
| 157 | 155 | { |
@@ -165,8 +163,7 @@ discard block |
||
| 165 | 163 | if($oCacheHandler->isSupport()) |
| 166 | 164 | { |
| 167 | 165 | $oCacheHandler->put($cache_key, $buff); |
| 168 | - } |
|
| 169 | - else |
|
| 166 | + } else |
|
| 170 | 167 | { |
| 171 | 168 | FileHandler::writeFile($this->compiled_file, $buff); |
| 172 | 169 | } |
@@ -286,8 +283,7 @@ discard block |
||
| 286 | 283 | { |
| 287 | 284 | $path = str_replace('@', '', $m[1]); |
| 288 | 285 | $path = './files/ruleset/' . $path . '.xml'; |
| 289 | - } |
|
| 290 | - else if(strpos($m[1], '#') !== FALSE) |
|
| 286 | + } else if(strpos($m[1], '#') !== FALSE) |
|
| 291 | 287 | { |
| 292 | 288 | $fileName = str_replace('#', '', $m[1]); |
| 293 | 289 | $fileName = str_replace('<?php echo ', '', $fileName); |
@@ -299,8 +295,7 @@ discard block |
||
| 299 | 295 | list($rulsetFile) = explode('.', $fileName); |
| 300 | 296 | $autoPath = $module_path . '/ruleset/' . $rulsetFile . '.xml'; |
| 301 | 297 | $m[1] = $rulsetFile; |
| 302 | - } |
|
| 303 | - else if(preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm)) |
|
| 298 | + } else if(preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm)) |
|
| 304 | 299 | { |
| 305 | 300 | $module_path = $mm[1]; |
| 306 | 301 | $path = $module_path . '/ruleset/' . $m[1] . '.xml'; |
@@ -330,10 +325,10 @@ discard block |
||
| 330 | 325 | if(!preg_match('/no-error-return-url="true"/i', $matches[1])) |
| 331 | 326 | { |
| 332 | 327 | preg_match('/<input[^>]*name="error_return_url"[^>]*>/is', $matches[2], $m3); |
| 333 | - if(!$m3[0]) |
|
| 334 | - $matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />' . $matches[2]; |
|
| 335 | - } |
|
| 336 | - else |
|
| 328 | + if(!$m3[0]) { |
|
| 329 | + $matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />' . $matches[2]; |
|
| 330 | + } |
|
| 331 | + } else |
|
| 337 | 332 | { |
| 338 | 333 | $matches[1] = preg_replace('/no-error-return-url="true"/i', '', $matches[1]); |
| 339 | 334 | } |
@@ -378,13 +373,11 @@ discard block |
||
| 378 | 373 | { |
| 379 | 374 | throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}"); |
| 380 | 375 | } |
| 381 | - } |
|
| 382 | - else |
|
| 376 | + } else |
|
| 383 | 377 | { |
| 384 | 378 | include(substr($buff, 7)); |
| 385 | 379 | } |
| 386 | - } |
|
| 387 | - else |
|
| 380 | + } else |
|
| 388 | 381 | { |
| 389 | 382 | $eval_str = "?>" . $buff; |
| 390 | 383 | @eval($eval_str); |
@@ -510,12 +503,10 @@ discard block |
||
| 510 | 503 | $expr_m[2] .= '=>' . trim($expr_m[3]); |
| 511 | 504 | } |
| 512 | 505 | $nodes[$idx - 1] .= "<?php if({$expr_m[1]}&&count({$expr_m[1]}))foreach({$expr_m[1]} as {$expr_m[2]}){ ?>"; |
| 513 | - } |
|
| 514 | - elseif($expr_m[4]) |
|
| 506 | + } elseif($expr_m[4]) |
|
| 515 | 507 | { |
| 516 | 508 | $nodes[$idx - 1] .= "<?php for({$expr_m[4]}){ ?>"; |
| 517 | - } |
|
| 518 | - elseif($expr_m[5]) |
|
| 509 | + } elseif($expr_m[5]) |
|
| 519 | 510 | { |
| 520 | 511 | $nodes[$idx - 1] .= "<?php while({$expr_m[5]}={$expr_m[6]}){ ?>"; |
| 521 | 512 | } |
@@ -530,8 +521,7 @@ discard block |
||
| 530 | 521 | if($node{1} == '!' || substr($node, -2, 1) == '/' || isset($self_closing[$tag])) |
| 531 | 522 | { |
| 532 | 523 | $nodes[$idx + 1] = $close_php . $nodes[$idx + 1]; |
| 533 | - } |
|
| 534 | - else |
|
| 524 | + } else |
|
| 535 | 525 | { |
| 536 | 526 | $depth = 1; |
| 537 | 527 | for($i = $idx + 2; $i < $node_len; $i+=2) |
@@ -540,8 +530,7 @@ discard block |
||
| 540 | 530 | if(strpos($nd, $tag) === 1) |
| 541 | 531 | { |
| 542 | 532 | $depth++; |
| 543 | - } |
|
| 544 | - elseif(strpos($nd, '/' . $tag) === 1) |
|
| 533 | + } elseif(strpos($nd, '/' . $tag) === 1) |
|
| 545 | 534 | { |
| 546 | 535 | $depth--; |
| 547 | 536 | if(!$depth) |
@@ -610,8 +599,7 @@ discard block |
||
| 610 | 599 | } |
| 611 | 600 | } |
| 612 | 601 | $attr['target'] = $m[5]; |
| 613 | - } |
|
| 614 | - else |
|
| 602 | + } else |
|
| 615 | 603 | { |
| 616 | 604 | if(!preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $mm)) |
| 617 | 605 | { |
@@ -690,8 +678,7 @@ discard block |
||
| 690 | 678 | if($pathinfo['basename'] == 'lang.xml' || substr($pathinfo['dirname'], -5) == '/lang') |
| 691 | 679 | { |
| 692 | 680 | $result = "Context::loadLang('{$relativeDir}');"; |
| 693 | - } |
|
| 694 | - else |
|
| 681 | + } else |
|
| 695 | 682 | { |
| 696 | 683 | $result = "require_once('./classes/xml/XmlJsFilter.class.php');\$__xmlFilter=new XmlJsFilter('{$relativeDir}','{$pathinfo['basename']}');\$__xmlFilter->compile();"; |
| 697 | 684 | } |
@@ -700,8 +687,7 @@ discard block |
||
| 700 | 687 | if($doUnload) |
| 701 | 688 | { |
| 702 | 689 | $result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}');"; |
| 703 | - } |
|
| 704 | - else |
|
| 690 | + } else |
|
| 705 | 691 | { |
| 706 | 692 | $metafile = $attr['target']; |
| 707 | 693 | $result = "\$__tmp=array('{$attr['target']}','{$attr['type']}','{$attr['targetie']}','{$attr['index']}');Context::loadFile(\$__tmp);unset(\$__tmp);"; |
@@ -711,8 +697,7 @@ discard block |
||
| 711 | 697 | if($doUnload) |
| 712 | 698 | { |
| 713 | 699 | $result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}','{$attr['media']}');"; |
| 714 | - } |
|
| 715 | - else |
|
| 700 | + } else |
|
| 716 | 701 | { |
| 717 | 702 | $metafile = $attr['target']; |
| 718 | 703 | $result = "\$__tmp=array('{$attr['target']}','{$attr['media']}','{$attr['targetie']}','{$attr['index']}');Context::loadFile(\$__tmp);unset(\$__tmp);"; |
@@ -753,8 +738,7 @@ discard block |
||
| 753 | 738 | if($mm[1] == 'switch') |
| 754 | 739 | { |
| 755 | 740 | $m[9] = ''; |
| 756 | - } |
|
| 757 | - elseif($mm[1] == 'foreach') |
|
| 741 | + } elseif($mm[1] == 'foreach') |
|
| 758 | 742 | { |
| 759 | 743 | $var = preg_replace('/^\s*\(\s*(.+?) .*$/', '$1', $m[8]); |
| 760 | 744 | $precheck = "if({$var}&&count({$var}))"; |
@@ -16,7 +16,7 @@ discard block |
||
| 16 | 16 | private $path = NULL; ///< target directory |
| 17 | 17 | private $filename = NULL; ///< target filename |
| 18 | 18 | private $file = NULL; ///< target file (fullpath) |
| 19 | - private $xe_path = NULL; ///< XpressEngine base path |
|
| 19 | + private $xe_path = NULL; ///< XpressEngine base path |
|
| 20 | 20 | private $web_path = NULL; ///< tpl file web path |
| 21 | 21 | private $compiled_file = NULL; ///< tpl file web path |
| 22 | 22 | private $skipTags = NULL; |
@@ -30,7 +30,7 @@ discard block |
||
| 30 | 30 | public function __construct() |
| 31 | 31 | { |
| 32 | 32 | $this->xe_path = rtrim(getScriptPath(), '/'); |
| 33 | - $this->compiled_path = _XE_PATH_ . $this->compiled_path; |
|
| 33 | + $this->compiled_path = _XE_PATH_.$this->compiled_path; |
|
| 34 | 34 | } |
| 35 | 35 | |
| 36 | 36 | /** |
@@ -41,9 +41,9 @@ discard block |
||
| 41 | 41 | { |
| 42 | 42 | static $oTemplate = NULL; |
| 43 | 43 | |
| 44 | - if(__DEBUG__ == 3) |
|
| 44 | + if (__DEBUG__ == 3) |
|
| 45 | 45 | { |
| 46 | - if(!isset($GLOBALS['__TemplateHandlerCalled__'])) |
|
| 46 | + if (!isset($GLOBALS['__TemplateHandlerCalled__'])) |
|
| 47 | 47 | { |
| 48 | 48 | $GLOBALS['__TemplateHandlerCalled__'] = 1; |
| 49 | 49 | } |
@@ -53,7 +53,7 @@ discard block |
||
| 53 | 53 | } |
| 54 | 54 | } |
| 55 | 55 | |
| 56 | - if(!$oTemplate) |
|
| 56 | + if (!$oTemplate) |
|
| 57 | 57 | { |
| 58 | 58 | $oTemplate = new TemplateHandler(); |
| 59 | 59 | } |
@@ -71,23 +71,23 @@ discard block |
||
| 71 | 71 | protected function init($tpl_path, $tpl_filename, $tpl_file = '') |
| 72 | 72 | { |
| 73 | 73 | // verify arguments |
| 74 | - if(substr($tpl_path, -1) != '/') |
|
| 74 | + if (substr($tpl_path, -1) != '/') |
|
| 75 | 75 | { |
| 76 | 76 | $tpl_path .= '/'; |
| 77 | 77 | } |
| 78 | - if(!is_dir($tpl_path)) |
|
| 78 | + if (!is_dir($tpl_path)) |
|
| 79 | 79 | { |
| 80 | 80 | return; |
| 81 | 81 | } |
| 82 | - if(!file_exists($tpl_path . $tpl_filename) && file_exists($tpl_path . $tpl_filename . '.html')) |
|
| 82 | + if (!file_exists($tpl_path.$tpl_filename) && file_exists($tpl_path.$tpl_filename.'.html')) |
|
| 83 | 83 | { |
| 84 | 84 | $tpl_filename .= '.html'; |
| 85 | 85 | } |
| 86 | 86 | |
| 87 | 87 | // create tpl_file variable |
| 88 | - if(!$tpl_file) |
|
| 88 | + if (!$tpl_file) |
|
| 89 | 89 | { |
| 90 | - $tpl_file = $tpl_path . $tpl_filename; |
|
| 90 | + $tpl_file = $tpl_path.$tpl_filename; |
|
| 91 | 91 | } |
| 92 | 92 | |
| 93 | 93 | // set template file infos. |
@@ -95,10 +95,10 @@ discard block |
||
| 95 | 95 | $this->filename = $tpl_filename; |
| 96 | 96 | $this->file = $tpl_file; |
| 97 | 97 | |
| 98 | - $this->web_path = $this->xe_path . '/' . ltrim(preg_replace('@^' . preg_quote(_XE_PATH_, '@') . '|\./@', '', $this->path), '/'); |
|
| 98 | + $this->web_path = $this->xe_path.'/'.ltrim(preg_replace('@^'.preg_quote(_XE_PATH_, '@').'|\./@', '', $this->path), '/'); |
|
| 99 | 99 | |
| 100 | 100 | // get compiled file name |
| 101 | - $hash = md5($this->file . __XE_VERSION__); |
|
| 101 | + $hash = md5($this->file.__XE_VERSION__); |
|
| 102 | 102 | $this->compiled_file = "{$this->compiled_path}{$hash}.compiled.php"; |
| 103 | 103 | |
| 104 | 104 | // compare various file's modified time for check changed |
@@ -119,7 +119,7 @@ discard block |
||
| 119 | 119 | $buff = false; |
| 120 | 120 | |
| 121 | 121 | // store the starting time for debug information |
| 122 | - if(__DEBUG__ == 3) |
|
| 122 | + if (__DEBUG__ == 3) |
|
| 123 | 123 | { |
| 124 | 124 | $start = getMicroTime(); |
| 125 | 125 | } |
@@ -128,13 +128,13 @@ discard block |
||
| 128 | 128 | $this->init($tpl_path, $tpl_filename, $tpl_file); |
| 129 | 129 | |
| 130 | 130 | // if target file does not exist exit |
| 131 | - if(!$this->file || !file_exists($this->file)) |
|
| 131 | + if (!$this->file || !file_exists($this->file)) |
|
| 132 | 132 | { |
| 133 | 133 | return "Err : '{$this->file}' template file does not exists."; |
| 134 | 134 | } |
| 135 | 135 | |
| 136 | 136 | // for backward compatibility |
| 137 | - if(is_null(self::$rootTpl)) |
|
| 137 | + if (is_null(self::$rootTpl)) |
|
| 138 | 138 | { |
| 139 | 139 | self::$rootTpl = $this->file; |
| 140 | 140 | } |
@@ -146,23 +146,23 @@ discard block |
||
| 146 | 146 | $oCacheHandler = CacheHandler::getInstance('template'); |
| 147 | 147 | |
| 148 | 148 | // get cached buff |
| 149 | - if($oCacheHandler->isSupport()) |
|
| 149 | + if ($oCacheHandler->isSupport()) |
|
| 150 | 150 | { |
| 151 | - $cache_key = 'template:' . $this->file; |
|
| 151 | + $cache_key = 'template:'.$this->file; |
|
| 152 | 152 | $buff = $oCacheHandler->get($cache_key, $latest_mtime); |
| 153 | 153 | } |
| 154 | 154 | else |
| 155 | 155 | { |
| 156 | - if(is_readable($this->compiled_file) && filemtime($this->compiled_file) > $latest_mtime && filesize($this->compiled_file)) |
|
| 156 | + if (is_readable($this->compiled_file) && filemtime($this->compiled_file) > $latest_mtime && filesize($this->compiled_file)) |
|
| 157 | 157 | { |
| 158 | - $buff = 'file://' . $this->compiled_file; |
|
| 158 | + $buff = 'file://'.$this->compiled_file; |
|
| 159 | 159 | } |
| 160 | 160 | } |
| 161 | 161 | |
| 162 | - if($buff === FALSE) |
|
| 162 | + if ($buff === FALSE) |
|
| 163 | 163 | { |
| 164 | 164 | $buff = $this->parse(); |
| 165 | - if($oCacheHandler->isSupport()) |
|
| 165 | + if ($oCacheHandler->isSupport()) |
|
| 166 | 166 | { |
| 167 | 167 | $oCacheHandler->put($cache_key, $buff); |
| 168 | 168 | } |
@@ -174,13 +174,13 @@ discard block |
||
| 174 | 174 | |
| 175 | 175 | $output = $this->_fetch($buff); |
| 176 | 176 | |
| 177 | - if($__templatehandler_root_tpl == $this->file) |
|
| 177 | + if ($__templatehandler_root_tpl == $this->file) |
|
| 178 | 178 | { |
| 179 | 179 | $__templatehandler_root_tpl = null; |
| 180 | 180 | } |
| 181 | 181 | |
| 182 | 182 | // store the ending time for debug information |
| 183 | - if(__DEBUG__ == 3) |
|
| 183 | + if (__DEBUG__ == 3) |
|
| 184 | 184 | { |
| 185 | 185 | $GLOBALS['__template_elapsed__'] += getMicroTime() - $start; |
| 186 | 186 | } |
@@ -199,7 +199,7 @@ discard block |
||
| 199 | 199 | $this->init($tpl_path, $tpl_filename, null); |
| 200 | 200 | |
| 201 | 201 | // if target file does not exist exit |
| 202 | - if(!$this->file || !file_exists($this->file)) |
|
| 202 | + if (!$this->file || !file_exists($this->file)) |
|
| 203 | 203 | { |
| 204 | 204 | Context::close(); |
| 205 | 205 | exit("Cannot find the template file: '{$this->file}'"); |
@@ -215,9 +215,9 @@ discard block |
||
| 215 | 215 | */ |
| 216 | 216 | protected function parse($buff = null) |
| 217 | 217 | { |
| 218 | - if(is_null($buff)) |
|
| 218 | + if (is_null($buff)) |
|
| 219 | 219 | { |
| 220 | - if(!is_readable($this->file)) |
|
| 220 | + if (!is_readable($this->file)) |
|
| 221 | 221 | { |
| 222 | 222 | return; |
| 223 | 223 | } |
@@ -227,7 +227,7 @@ discard block |
||
| 227 | 227 | } |
| 228 | 228 | |
| 229 | 229 | // HTML tags to skip |
| 230 | - if(is_null($this->skipTags)) |
|
| 230 | + if (is_null($this->skipTags)) |
|
| 231 | 231 | { |
| 232 | 232 | $this->skipTags = array('marquee'); |
| 233 | 233 | } |
@@ -249,13 +249,13 @@ discard block |
||
| 249 | 249 | |
| 250 | 250 | // form auto generation |
| 251 | 251 | $temp = preg_replace_callback('/(<form(?:<\?php.+?\?>|[^<>]+)*?>)(.*?)(<\/form>)/is', array($this, '_compileFormAuthGeneration'), $buff); |
| 252 | - if($temp) |
|
| 252 | + if ($temp) |
|
| 253 | 253 | { |
| 254 | 254 | $buff = $temp; |
| 255 | 255 | } |
| 256 | 256 | |
| 257 | 257 | // prevent from calling directly before writing into file |
| 258 | - $buff = '<?php if(!defined("__XE__"))exit;?>' . $buff; |
|
| 258 | + $buff = '<?php if(!defined("__XE__"))exit;?>'.$buff; |
|
| 259 | 259 | |
| 260 | 260 | // remove php script reopening |
| 261 | 261 | $buff = preg_replace(array('/(\n|\r\n)+/', '/(;)?( )*\?\>\<\?php([\n\t ]+)?/'), array("\n", ";\n"), $buff); |
@@ -275,40 +275,40 @@ discard block |
||
| 275 | 275 | private function _compileFormAuthGeneration($matches) |
| 276 | 276 | { |
| 277 | 277 | // form ruleset attribute move to hidden tag |
| 278 | - if($matches[1]) |
|
| 278 | + if ($matches[1]) |
|
| 279 | 279 | { |
| 280 | 280 | preg_match('/ruleset="([^"]*?)"/is', $matches[1], $m); |
| 281 | - if($m[0]) |
|
| 281 | + if ($m[0]) |
|
| 282 | 282 | { |
| 283 | - $matches[1] = preg_replace('/' . addcslashes($m[0], '?$') . '/i', '', $matches[1]); |
|
| 283 | + $matches[1] = preg_replace('/'.addcslashes($m[0], '?$').'/i', '', $matches[1]); |
|
| 284 | 284 | |
| 285 | - if(strpos($m[1], '@') !== FALSE) |
|
| 285 | + if (strpos($m[1], '@') !== FALSE) |
|
| 286 | 286 | { |
| 287 | 287 | $path = str_replace('@', '', $m[1]); |
| 288 | - $path = './files/ruleset/' . $path . '.xml'; |
|
| 288 | + $path = './files/ruleset/'.$path.'.xml'; |
|
| 289 | 289 | } |
| 290 | - else if(strpos($m[1], '#') !== FALSE) |
|
| 290 | + else if (strpos($m[1], '#') !== FALSE) |
|
| 291 | 291 | { |
| 292 | 292 | $fileName = str_replace('#', '', $m[1]); |
| 293 | 293 | $fileName = str_replace('<?php echo ', '', $fileName); |
| 294 | 294 | $fileName = str_replace(' ?>', '', $fileName); |
| 295 | - $path = '#./files/ruleset/' . $fileName . '.xml'; |
|
| 295 | + $path = '#./files/ruleset/'.$fileName.'.xml'; |
|
| 296 | 296 | |
| 297 | 297 | preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm); |
| 298 | 298 | $module_path = $mm[1]; |
| 299 | 299 | list($rulsetFile) = explode('.', $fileName); |
| 300 | - $autoPath = $module_path . '/ruleset/' . $rulsetFile . '.xml'; |
|
| 300 | + $autoPath = $module_path.'/ruleset/'.$rulsetFile.'.xml'; |
|
| 301 | 301 | $m[1] = $rulsetFile; |
| 302 | 302 | } |
| 303 | - else if(preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm)) |
|
| 303 | + else if (preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm)) |
|
| 304 | 304 | { |
| 305 | 305 | $module_path = $mm[1]; |
| 306 | - $path = $module_path . '/ruleset/' . $m[1] . '.xml'; |
|
| 306 | + $path = $module_path.'/ruleset/'.$m[1].'.xml'; |
|
| 307 | 307 | } |
| 308 | 308 | |
| 309 | - $matches[2] = '<input type="hidden" name="ruleset" value="' . $m[1] . '" />' . $matches[2]; |
|
| 309 | + $matches[2] = '<input type="hidden" name="ruleset" value="'.$m[1].'" />'.$matches[2]; |
|
| 310 | 310 | //assign to addJsFile method for js dynamic recache |
| 311 | - $matches[1] = '<?php Context::addJsFile("' . $path . '", FALSE, "", 0, "body", TRUE, "' . $autoPath . '") ?' . '>' . $matches[1]; |
|
| 311 | + $matches[1] = '<?php Context::addJsFile("'.$path.'", FALSE, "", 0, "body", TRUE, "'.$autoPath.'") ?'.'>'.$matches[1]; |
|
| 312 | 312 | } |
| 313 | 313 | } |
| 314 | 314 | |
@@ -316,22 +316,22 @@ discard block |
||
| 316 | 316 | preg_match_all('/<input[^>]* name="(act|mid|vid)"/is', $matches[2], $m2); |
| 317 | 317 | $checkVar = array('act', 'mid', 'vid'); |
| 318 | 318 | $resultArray = array_diff($checkVar, $m2[1]); |
| 319 | - if(is_array($resultArray)) |
|
| 319 | + if (is_array($resultArray)) |
|
| 320 | 320 | { |
| 321 | 321 | $generatedHidden = ''; |
| 322 | - foreach($resultArray AS $key => $value) |
|
| 322 | + foreach ($resultArray AS $key => $value) |
|
| 323 | 323 | { |
| 324 | - $generatedHidden .= '<input type="hidden" name="' . $value . '" value="<?php echo $__Context->' . $value . ' ?>" />'; |
|
| 324 | + $generatedHidden .= '<input type="hidden" name="'.$value.'" value="<?php echo $__Context->'.$value.' ?>" />'; |
|
| 325 | 325 | } |
| 326 | - $matches[2] = $generatedHidden . $matches[2]; |
|
| 326 | + $matches[2] = $generatedHidden.$matches[2]; |
|
| 327 | 327 | } |
| 328 | 328 | |
| 329 | 329 | // return url generate |
| 330 | - if(!preg_match('/no-error-return-url="true"/i', $matches[1])) |
|
| 330 | + if (!preg_match('/no-error-return-url="true"/i', $matches[1])) |
|
| 331 | 331 | { |
| 332 | 332 | preg_match('/<input[^>]*name="error_return_url"[^>]*>/is', $matches[2], $m3); |
| 333 | - if(!$m3[0]) |
|
| 334 | - $matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />' . $matches[2]; |
|
| 333 | + if (!$m3[0]) |
|
| 334 | + $matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />'.$matches[2]; |
|
| 335 | 335 | } |
| 336 | 336 | else |
| 337 | 337 | { |
@@ -349,7 +349,7 @@ discard block |
||
| 349 | 349 | */ |
| 350 | 350 | private function _fetch($buff) |
| 351 | 351 | { |
| 352 | - if(!$buff) |
|
| 352 | + if (!$buff) |
|
| 353 | 353 | { |
| 354 | 354 | return; |
| 355 | 355 | } |
@@ -357,20 +357,20 @@ discard block |
||
| 357 | 357 | $__Context = &$GLOBALS['__Context__']; |
| 358 | 358 | $__Context->tpl_path = $this->path; |
| 359 | 359 | |
| 360 | - if($_SESSION['is_logged']) |
|
| 360 | + if ($_SESSION['is_logged']) |
|
| 361 | 361 | { |
| 362 | 362 | $__Context->logged_info = Context::get('logged_info'); |
| 363 | 363 | } |
| 364 | 364 | |
| 365 | 365 | $level = ob_get_level(); |
| 366 | 366 | ob_start(); |
| 367 | - if(substr($buff, 0, 7) == 'file://') |
|
| 367 | + if (substr($buff, 0, 7) == 'file://') |
|
| 368 | 368 | { |
| 369 | - if(__DEBUG__) |
|
| 369 | + if (__DEBUG__) |
|
| 370 | 370 | { |
| 371 | 371 | //load cache file from disk |
| 372 | 372 | $eval_str = FileHandler::readFile(substr($buff, 7)); |
| 373 | - $eval_str_buffed = "?>" . $eval_str; |
|
| 373 | + $eval_str_buffed = "?>".$eval_str; |
|
| 374 | 374 | @eval($eval_str_buffed); |
| 375 | 375 | $error_info = error_get_last(); |
| 376 | 376 | //parse error |
@@ -386,7 +386,7 @@ discard block |
||
| 386 | 386 | } |
| 387 | 387 | else |
| 388 | 388 | { |
| 389 | - $eval_str = "?>" . $buff; |
|
| 389 | + $eval_str = "?>".$buff; |
|
| 390 | 390 | @eval($eval_str); |
| 391 | 391 | $error_info = error_get_last(); |
| 392 | 392 | //parse error |
@@ -415,31 +415,31 @@ discard block |
||
| 415 | 415 | private function _replacePath($match) |
| 416 | 416 | { |
| 417 | 417 | //return origin conde when src value started '${'. |
| 418 | - if(preg_match('@^\${@', $match[1])) |
|
| 418 | + if (preg_match('@^\${@', $match[1])) |
|
| 419 | 419 | { |
| 420 | 420 | return $match[0]; |
| 421 | 421 | } |
| 422 | 422 | |
| 423 | 423 | //return origin code when src value include variable. |
| 424 | - if(preg_match('@^[\'|"]\s*\.\s*\$@', $match[1])) |
|
| 424 | + if (preg_match('@^[\'|"]\s*\.\s*\$@', $match[1])) |
|
| 425 | 425 | { |
| 426 | 426 | return $match[0]; |
| 427 | 427 | } |
| 428 | 428 | |
| 429 | 429 | $src = preg_replace('@^(\./)+@', '', trim($match[1])); |
| 430 | 430 | |
| 431 | - $src = $this->web_path . $src; |
|
| 431 | + $src = $this->web_path.$src; |
|
| 432 | 432 | $src = str_replace('/./', '/', $src); |
| 433 | 433 | |
| 434 | 434 | // for backward compatibility |
| 435 | 435 | $src = preg_replace('@/((?:[\w-]+/)+)\1@', '/\1', $src); |
| 436 | 436 | |
| 437 | - while(($tmp = preg_replace('@[^/]+/\.\./@', '', $src, 1)) !== $src) |
|
| 437 | + while (($tmp = preg_replace('@[^/]+/\.\./@', '', $src, 1)) !== $src) |
|
| 438 | 438 | { |
| 439 | 439 | $src = $tmp; |
| 440 | 440 | } |
| 441 | 441 | |
| 442 | - return substr($match[0], 0, -strlen($match[1]) - 6) . "src=\"{$src}\""; |
|
| 442 | + return substr($match[0], 0, -strlen($match[1]) - 6)."src=\"{$src}\""; |
|
| 443 | 443 | } |
| 444 | 444 | |
| 445 | 445 | /** |
@@ -449,19 +449,19 @@ discard block |
||
| 449 | 449 | */ |
| 450 | 450 | private function _parseInline($buff) |
| 451 | 451 | { |
| 452 | - if(preg_match_all('/<([a-zA-Z]+\d?)(?>(?!<[a-z]+\d?[\s>]).)*?(?:[ \|]cond| loop)="/s', $buff, $match) === false) |
|
| 452 | + if (preg_match_all('/<([a-zA-Z]+\d?)(?>(?!<[a-z]+\d?[\s>]).)*?(?:[ \|]cond| loop)="/s', $buff, $match) === false) |
|
| 453 | 453 | { |
| 454 | 454 | return $buff; |
| 455 | 455 | } |
| 456 | 456 | |
| 457 | 457 | $tags = array_diff(array_unique($match[1]), $this->skipTags); |
| 458 | 458 | |
| 459 | - if(!count($tags)) |
|
| 459 | + if (!count($tags)) |
|
| 460 | 460 | { |
| 461 | 461 | return $buff; |
| 462 | 462 | } |
| 463 | 463 | |
| 464 | - $tags = '(?:' . implode('|', $tags) . ')'; |
|
| 464 | + $tags = '(?:'.implode('|', $tags).')'; |
|
| 465 | 465 | $split_regex = "@(<(?>/?{$tags})(?>[^<>\{\}\"']+|<!--.*?-->|{[^}]+}|\".*?\"|'.*?'|.)*?>)@s"; |
| 466 | 466 | |
| 467 | 467 | $nodes = preg_split($split_regex, $buff, -1, PREG_SPLIT_DELIM_CAPTURE); |
@@ -469,14 +469,14 @@ discard block |
||
| 469 | 469 | // list of self closing tags |
| 470 | 470 | $self_closing = array('area' => 1, 'base' => 1, 'basefont' => 1, 'br' => 1, 'hr' => 1, 'input' => 1, 'img' => 1, 'link' => 1, 'meta' => 1, 'param' => 1, 'frame' => 1, 'col' => 1); |
| 471 | 471 | |
| 472 | - for($idx = 1, $node_len = count($nodes); $idx < $node_len; $idx+=2) |
|
| 472 | + for ($idx = 1, $node_len = count($nodes); $idx < $node_len; $idx += 2) |
|
| 473 | 473 | { |
| 474 | - if(!($node = $nodes[$idx])) |
|
| 474 | + if (!($node = $nodes[$idx])) |
|
| 475 | 475 | { |
| 476 | 476 | continue; |
| 477 | 477 | } |
| 478 | 478 | |
| 479 | - if(preg_match_all('@\s(loop|cond)="([^"]+)"@', $node, $matches)) |
|
| 479 | + if (preg_match_all('@\s(loop|cond)="([^"]+)"@', $node, $matches)) |
|
| 480 | 480 | { |
| 481 | 481 | // this tag |
| 482 | 482 | $tag = substr($node, 1, strpos($node, ' ') - 1); |
@@ -485,37 +485,37 @@ discard block |
||
| 485 | 485 | $closing = 0; |
| 486 | 486 | |
| 487 | 487 | // process opening tag |
| 488 | - foreach($matches[1] as $n => $stmt) |
|
| 488 | + foreach ($matches[1] as $n => $stmt) |
|
| 489 | 489 | { |
| 490 | 490 | $expr = $matches[2][$n]; |
| 491 | 491 | $expr = $this->_replaceVar($expr); |
| 492 | 492 | $closing++; |
| 493 | 493 | |
| 494 | - switch($stmt) |
|
| 494 | + switch ($stmt) |
|
| 495 | 495 | { |
| 496 | 496 | case 'cond': |
| 497 | 497 | $nodes[$idx - 1] .= "<?php if({$expr}){ ?>"; |
| 498 | 498 | break; |
| 499 | 499 | case 'loop': |
| 500 | - if(!preg_match('@^(?:(.+?)=>(.+?)(?:,(.+?))?|(.*?;.*?;.*?)|(.+?)\s*=\s*(.+?))$@', $expr, $expr_m)) |
|
| 500 | + if (!preg_match('@^(?:(.+?)=>(.+?)(?:,(.+?))?|(.*?;.*?;.*?)|(.+?)\s*=\s*(.+?))$@', $expr, $expr_m)) |
|
| 501 | 501 | { |
| 502 | 502 | break; |
| 503 | 503 | } |
| 504 | - if($expr_m[1]) |
|
| 504 | + if ($expr_m[1]) |
|
| 505 | 505 | { |
| 506 | 506 | $expr_m[1] = trim($expr_m[1]); |
| 507 | 507 | $expr_m[2] = trim($expr_m[2]); |
| 508 | - if($expr_m[3]) |
|
| 508 | + if ($expr_m[3]) |
|
| 509 | 509 | { |
| 510 | - $expr_m[2] .= '=>' . trim($expr_m[3]); |
|
| 510 | + $expr_m[2] .= '=>'.trim($expr_m[3]); |
|
| 511 | 511 | } |
| 512 | 512 | $nodes[$idx - 1] .= "<?php if({$expr_m[1]}&&count({$expr_m[1]}))foreach({$expr_m[1]} as {$expr_m[2]}){ ?>"; |
| 513 | 513 | } |
| 514 | - elseif($expr_m[4]) |
|
| 514 | + elseif ($expr_m[4]) |
|
| 515 | 515 | { |
| 516 | 516 | $nodes[$idx - 1] .= "<?php for({$expr_m[4]}){ ?>"; |
| 517 | 517 | } |
| 518 | - elseif($expr_m[5]) |
|
| 518 | + elseif ($expr_m[5]) |
|
| 519 | 519 | { |
| 520 | 520 | $nodes[$idx - 1] .= "<?php while({$expr_m[5]}={$expr_m[6]}){ ?>"; |
| 521 | 521 | } |
@@ -525,28 +525,28 @@ discard block |
||
| 525 | 525 | $node = preg_replace('@\s(loop|cond)="([^"]+)"@', '', $node); |
| 526 | 526 | |
| 527 | 527 | // find closing tag |
| 528 | - $close_php = '<?php ' . str_repeat('}', $closing) . ' ?>'; |
|
| 528 | + $close_php = '<?php '.str_repeat('}', $closing).' ?>'; |
|
| 529 | 529 | // self closing tag |
| 530 | - if($node{1} == '!' || substr($node, -2, 1) == '/' || isset($self_closing[$tag])) |
|
| 530 | + if ($node{1} == '!' || substr($node, -2, 1) == '/' || isset($self_closing[$tag])) |
|
| 531 | 531 | { |
| 532 | - $nodes[$idx + 1] = $close_php . $nodes[$idx + 1]; |
|
| 532 | + $nodes[$idx + 1] = $close_php.$nodes[$idx + 1]; |
|
| 533 | 533 | } |
| 534 | 534 | else |
| 535 | 535 | { |
| 536 | 536 | $depth = 1; |
| 537 | - for($i = $idx + 2; $i < $node_len; $i+=2) |
|
| 537 | + for ($i = $idx + 2; $i < $node_len; $i += 2) |
|
| 538 | 538 | { |
| 539 | 539 | $nd = $nodes[$i]; |
| 540 | - if(strpos($nd, $tag) === 1) |
|
| 540 | + if (strpos($nd, $tag) === 1) |
|
| 541 | 541 | { |
| 542 | 542 | $depth++; |
| 543 | 543 | } |
| 544 | - elseif(strpos($nd, '/' . $tag) === 1) |
|
| 544 | + elseif (strpos($nd, '/'.$tag) === 1) |
|
| 545 | 545 | { |
| 546 | 546 | $depth--; |
| 547 | - if(!$depth) |
|
| 547 | + if (!$depth) |
|
| 548 | 548 | { |
| 549 | - $nodes[$i - 1] .= $nodes[$i] . $close_php; |
|
| 549 | + $nodes[$i - 1] .= $nodes[$i].$close_php; |
|
| 550 | 550 | $nodes[$i] = ''; |
| 551 | 551 | break; |
| 552 | 552 | } |
@@ -555,13 +555,13 @@ discard block |
||
| 555 | 555 | } |
| 556 | 556 | } |
| 557 | 557 | |
| 558 | - if(strpos($node, '|cond="') !== false) |
|
| 558 | + if (strpos($node, '|cond="') !== false) |
|
| 559 | 559 | { |
| 560 | 560 | $node = preg_replace('@(\s[-\w:]+(?:="[^"]+?")?)\|cond="(.+?)"@s', '<?php if($2){ ?>$1<?php } ?>', $node); |
| 561 | 561 | $node = $this->_replaceVar($node); |
| 562 | 562 | } |
| 563 | 563 | |
| 564 | - if($nodes[$idx] != $node) |
|
| 564 | + if ($nodes[$idx] != $node) |
|
| 565 | 565 | { |
| 566 | 566 | $nodes[$idx] = $node; |
| 567 | 567 | } |
@@ -581,30 +581,30 @@ discard block |
||
| 581 | 581 | private function _parseResource($m) |
| 582 | 582 | { |
| 583 | 583 | // {@ ... } or {$var} or {func(...)} |
| 584 | - if($m[1]) |
|
| 584 | + if ($m[1]) |
|
| 585 | 585 | { |
| 586 | - if(preg_match('@^(\w+)\(@', $m[1], $mm) && !function_exists($mm[1])) |
|
| 586 | + if (preg_match('@^(\w+)\(@', $m[1], $mm) && !function_exists($mm[1])) |
|
| 587 | 587 | { |
| 588 | 588 | return $m[0]; |
| 589 | 589 | } |
| 590 | 590 | |
| 591 | 591 | $echo = 'echo '; |
| 592 | - if($m[1]{0} == '@') |
|
| 592 | + if ($m[1]{0} == '@') |
|
| 593 | 593 | { |
| 594 | 594 | $echo = ''; |
| 595 | 595 | $m[1] = substr($m[1], 1); |
| 596 | 596 | } |
| 597 | - return '<?php ' . $echo . $this->_replaceVar($m[1]) . ' ?>'; |
|
| 597 | + return '<?php '.$echo.$this->_replaceVar($m[1]).' ?>'; |
|
| 598 | 598 | } |
| 599 | 599 | |
| 600 | - if($m[3]) |
|
| 600 | + if ($m[3]) |
|
| 601 | 601 | { |
| 602 | 602 | $attr = array(); |
| 603 | - if($m[5]) |
|
| 603 | + if ($m[5]) |
|
| 604 | 604 | { |
| 605 | - if(preg_match_all('@,(\w+)="([^"]+)"@', $m[6], $mm)) |
|
| 605 | + if (preg_match_all('@,(\w+)="([^"]+)"@', $m[6], $mm)) |
|
| 606 | 606 | { |
| 607 | - foreach($mm[1] as $idx => $name) |
|
| 607 | + foreach ($mm[1] as $idx => $name) |
|
| 608 | 608 | { |
| 609 | 609 | $attr[$name] = $mm[2][$idx]; |
| 610 | 610 | } |
@@ -613,21 +613,21 @@ discard block |
||
| 613 | 613 | } |
| 614 | 614 | else |
| 615 | 615 | { |
| 616 | - if(!preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $mm)) |
|
| 616 | + if (!preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $mm)) |
|
| 617 | 617 | { |
| 618 | 618 | return $m[0]; |
| 619 | 619 | } |
| 620 | - foreach($mm[1] as $idx => $name) |
|
| 620 | + foreach ($mm[1] as $idx => $name) |
|
| 621 | 621 | { |
| 622 | 622 | $attr[$name] = $mm[2][$idx]; |
| 623 | 623 | } |
| 624 | 624 | } |
| 625 | 625 | |
| 626 | - switch($m[3]) |
|
| 626 | + switch ($m[3]) |
|
| 627 | 627 | { |
| 628 | 628 | // <!--#include--> or <include ..> |
| 629 | 629 | case 'include': |
| 630 | - if(!$this->file || !$attr['target']) |
|
| 630 | + if (!$this->file || !$attr['target']) |
|
| 631 | 631 | { |
| 632 | 632 | return ''; |
| 633 | 633 | } |
@@ -635,7 +635,7 @@ discard block |
||
| 635 | 635 | $pathinfo = pathinfo($attr['target']); |
| 636 | 636 | $fileDir = $this->_getRelativeDir($pathinfo['dirname']); |
| 637 | 637 | |
| 638 | - if(!$fileDir) |
|
| 638 | + if (!$fileDir) |
|
| 639 | 639 | { |
| 640 | 640 | return ''; |
| 641 | 641 | } |
@@ -645,7 +645,7 @@ discard block |
||
| 645 | 645 | case 'load_js_plugin': |
| 646 | 646 | $plugin = $this->_replaceVar($m[5]); |
| 647 | 647 | $s = "<!--#JSPLUGIN:{$plugin}-->"; |
| 648 | - if(strpos($plugin, '$__Context') === false) |
|
| 648 | + if (strpos($plugin, '$__Context') === false) |
|
| 649 | 649 | { |
| 650 | 650 | $plugin = "'{$plugin}'"; |
| 651 | 651 | } |
@@ -661,13 +661,13 @@ discard block |
||
| 661 | 661 | $doUnload = ($m[3] === 'unload'); |
| 662 | 662 | $isRemote = !!preg_match('@^(https?:)?//@i', $attr['target']); |
| 663 | 663 | |
| 664 | - if(!$isRemote) |
|
| 664 | + if (!$isRemote) |
|
| 665 | 665 | { |
| 666 | - if(!preg_match('@^\.?/@', $attr['target'])) |
|
| 666 | + if (!preg_match('@^\.?/@', $attr['target'])) |
|
| 667 | 667 | { |
| 668 | - $attr['target'] = './' . $attr['target']; |
|
| 668 | + $attr['target'] = './'.$attr['target']; |
|
| 669 | 669 | } |
| 670 | - if(substr($attr['target'], -5) == '/lang') |
|
| 670 | + if (substr($attr['target'], -5) == '/lang') |
|
| 671 | 671 | { |
| 672 | 672 | $pathinfo['dirname'] .= '/lang'; |
| 673 | 673 | $pathinfo['basename'] = ''; |
@@ -676,18 +676,18 @@ discard block |
||
| 676 | 676 | |
| 677 | 677 | $relativeDir = $this->_getRelativeDir($pathinfo['dirname']); |
| 678 | 678 | |
| 679 | - $attr['target'] = $relativeDir . '/' . $pathinfo['basename']; |
|
| 679 | + $attr['target'] = $relativeDir.'/'.$pathinfo['basename']; |
|
| 680 | 680 | } |
| 681 | 681 | |
| 682 | - switch($pathinfo['extension']) |
|
| 682 | + switch ($pathinfo['extension']) |
|
| 683 | 683 | { |
| 684 | 684 | case 'xml': |
| 685 | - if($isRemote || $doUnload) |
|
| 685 | + if ($isRemote || $doUnload) |
|
| 686 | 686 | { |
| 687 | 687 | return ''; |
| 688 | 688 | } |
| 689 | 689 | // language file? |
| 690 | - if($pathinfo['basename'] == 'lang.xml' || substr($pathinfo['dirname'], -5) == '/lang') |
|
| 690 | + if ($pathinfo['basename'] == 'lang.xml' || substr($pathinfo['dirname'], -5) == '/lang') |
|
| 691 | 691 | { |
| 692 | 692 | $result = "Context::loadLang('{$relativeDir}');"; |
| 693 | 693 | } |
@@ -697,7 +697,7 @@ discard block |
||
| 697 | 697 | } |
| 698 | 698 | break; |
| 699 | 699 | case 'js': |
| 700 | - if($doUnload) |
|
| 700 | + if ($doUnload) |
|
| 701 | 701 | { |
| 702 | 702 | $result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}');"; |
| 703 | 703 | } |
@@ -708,7 +708,7 @@ discard block |
||
| 708 | 708 | } |
| 709 | 709 | break; |
| 710 | 710 | case 'css': |
| 711 | - if($doUnload) |
|
| 711 | + if ($doUnload) |
|
| 712 | 712 | { |
| 713 | 713 | $result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}','{$attr['media']}');"; |
| 714 | 714 | } |
@@ -721,9 +721,9 @@ discard block |
||
| 721 | 721 | } |
| 722 | 722 | |
| 723 | 723 | $result = "<?php {$result} ?>"; |
| 724 | - if($metafile) |
|
| 724 | + if ($metafile) |
|
| 725 | 725 | { |
| 726 | - $result = "<!--#Meta:{$metafile}-->" . $result; |
|
| 726 | + $result = "<!--#Meta:{$metafile}-->".$result; |
|
| 727 | 727 | } |
| 728 | 728 | |
| 729 | 729 | return $result; |
@@ -731,45 +731,45 @@ discard block |
||
| 731 | 731 | } |
| 732 | 732 | |
| 733 | 733 | // <[email protected]> such as <!--@if($cond)-->, <!--@else-->, <!--@end--> |
| 734 | - if($m[7]) |
|
| 734 | + if ($m[7]) |
|
| 735 | 735 | { |
| 736 | 736 | $m[7] = substr($m[7], 1); |
| 737 | - if(!$m[7]) |
|
| 737 | + if (!$m[7]) |
|
| 738 | 738 | { |
| 739 | - return '<?php ' . $this->_replaceVar($m[8]) . '{ ?>' . $m[9]; |
|
| 739 | + return '<?php '.$this->_replaceVar($m[8]).'{ ?>'.$m[9]; |
|
| 740 | 740 | } |
| 741 | - if(!preg_match('/^(?:((?:end)?(?:if|switch|for(?:each)?|while)|end)|(else(?:if)?)|(break@)?(case|default)|(break))$/', $m[7], $mm)) |
|
| 741 | + if (!preg_match('/^(?:((?:end)?(?:if|switch|for(?:each)?|while)|end)|(else(?:if)?)|(break@)?(case|default)|(break))$/', $m[7], $mm)) |
|
| 742 | 742 | { |
| 743 | 743 | return ''; |
| 744 | 744 | } |
| 745 | - if($mm[1]) |
|
| 745 | + if ($mm[1]) |
|
| 746 | 746 | { |
| 747 | - if($mm[1]{0} == 'e') |
|
| 747 | + if ($mm[1]{0} == 'e') |
|
| 748 | 748 | { |
| 749 | - return '<?php } ?>' . $m[9]; |
|
| 749 | + return '<?php } ?>'.$m[9]; |
|
| 750 | 750 | } |
| 751 | 751 | |
| 752 | 752 | $precheck = ''; |
| 753 | - if($mm[1] == 'switch') |
|
| 753 | + if ($mm[1] == 'switch') |
|
| 754 | 754 | { |
| 755 | 755 | $m[9] = ''; |
| 756 | 756 | } |
| 757 | - elseif($mm[1] == 'foreach') |
|
| 757 | + elseif ($mm[1] == 'foreach') |
|
| 758 | 758 | { |
| 759 | 759 | $var = preg_replace('/^\s*\(\s*(.+?) .*$/', '$1', $m[8]); |
| 760 | 760 | $precheck = "if({$var}&&count({$var}))"; |
| 761 | 761 | } |
| 762 | - return '<?php ' . $this->_replaceVar($precheck . $m[7] . $m[8]) . '{ ?>' . $m[9]; |
|
| 762 | + return '<?php '.$this->_replaceVar($precheck.$m[7].$m[8]).'{ ?>'.$m[9]; |
|
| 763 | 763 | } |
| 764 | - if($mm[2]) |
|
| 764 | + if ($mm[2]) |
|
| 765 | 765 | { |
| 766 | - return "<?php }{$m[7]}" . $this->_replaceVar($m[8]) . "{ ?>" . $m[9]; |
|
| 766 | + return "<?php }{$m[7]}".$this->_replaceVar($m[8])."{ ?>".$m[9]; |
|
| 767 | 767 | } |
| 768 | - if($mm[4]) |
|
| 768 | + if ($mm[4]) |
|
| 769 | 769 | { |
| 770 | - return "<?php " . ($mm[3] ? 'break;' : '') . "{$m[7]} " . trim($m[8], '()') . ": ?>" . $m[9]; |
|
| 770 | + return "<?php ".($mm[3] ? 'break;' : '')."{$m[7]} ".trim($m[8], '()').": ?>".$m[9]; |
|
| 771 | 771 | } |
| 772 | - if($mm[5]) |
|
| 772 | + if ($mm[5]) |
|
| 773 | 773 | { |
| 774 | 774 | return "<?php break; ?>"; |
| 775 | 775 | } |
@@ -788,30 +788,30 @@ discard block |
||
| 788 | 788 | $_path = $path; |
| 789 | 789 | |
| 790 | 790 | $fileDir = strtr(realpath($this->path), '\\', '/'); |
| 791 | - if($path{0} != '/') |
|
| 791 | + if ($path{0} != '/') |
|
| 792 | 792 | { |
| 793 | - $path = strtr(realpath($fileDir . '/' . $path), '\\', '/'); |
|
| 793 | + $path = strtr(realpath($fileDir.'/'.$path), '\\', '/'); |
|
| 794 | 794 | } |
| 795 | 795 | |
| 796 | 796 | // for backward compatibility |
| 797 | - if(!$path) |
|
| 797 | + if (!$path) |
|
| 798 | 798 | { |
| 799 | 799 | $dirs = explode('/', $fileDir); |
| 800 | 800 | $paths = explode('/', $_path); |
| 801 | 801 | $idx = array_search($paths[0], $dirs); |
| 802 | 802 | |
| 803 | - if($idx !== false) |
|
| 803 | + if ($idx !== false) |
|
| 804 | 804 | { |
| 805 | - while($dirs[$idx] && $dirs[$idx] === $paths[0]) |
|
| 805 | + while ($dirs[$idx] && $dirs[$idx] === $paths[0]) |
|
| 806 | 806 | { |
| 807 | 807 | array_splice($dirs, $idx, 1); |
| 808 | 808 | array_shift($paths); |
| 809 | 809 | } |
| 810 | - $path = strtr(realpath($fileDir . '/' . implode('/', $paths)), '\\', '/'); |
|
| 810 | + $path = strtr(realpath($fileDir.'/'.implode('/', $paths)), '\\', '/'); |
|
| 811 | 811 | } |
| 812 | 812 | } |
| 813 | 813 | |
| 814 | - $path = preg_replace('/^' . preg_quote(_XE_PATH_, '/') . '/', '', $path); |
|
| 814 | + $path = preg_replace('/^'.preg_quote(_XE_PATH_, '/').'/', '', $path); |
|
| 815 | 815 | |
| 816 | 816 | return $path; |
| 817 | 817 | } |
@@ -823,7 +823,7 @@ discard block |
||
| 823 | 823 | */ |
| 824 | 824 | function _replaceVar($php) |
| 825 | 825 | { |
| 826 | - if(!strlen($php)) |
|
| 826 | + if (!strlen($php)) |
|
| 827 | 827 | { |
| 828 | 828 | return ''; |
| 829 | 829 | } |
@@ -239,7 +239,7 @@ discard block |
||
| 239 | 239 | |
| 240 | 240 | /** |
| 241 | 241 | * Validate the fields. If the fields aren't passed, validation will be execute on the Context variables. |
| 242 | - * @param array $fields Target fields. The keys of the array represents field's name, its values represents field's value. |
|
| 242 | + * @param array $fields_ Target fields. The keys of the array represents field's name, its values represents field's value. |
|
| 243 | 243 | * @return boolean TRUE if it is valid, FALSE otherwise. |
| 244 | 244 | */ |
| 245 | 245 | function validate($fields_ = null) |
@@ -456,7 +456,7 @@ discard block |
||
| 456 | 456 | |
| 457 | 457 | /** |
| 458 | 458 | * Log an error |
| 459 | - * @param $msg error message |
|
| 459 | + * @param string $msg error message |
|
| 460 | 460 | * @return boolean always false |
| 461 | 461 | */ |
| 462 | 462 | function error($field, $msg) |
@@ -81,8 +81,9 @@ discard block |
||
| 81 | 81 | $this->_filters = array(); |
| 82 | 82 | $this->_xml_ruleset = NULL; |
| 83 | 83 | |
| 84 | - if($xml_path) |
|
| 85 | - $this->load($xml_path); |
|
| 84 | + if($xml_path) { |
|
| 85 | + $this->load($xml_path); |
|
| 86 | + } |
|
| 86 | 87 | |
| 87 | 88 | // predefined rules |
| 88 | 89 | $this->addRule(array( |
@@ -247,8 +248,7 @@ discard block |
||
| 247 | 248 | if(is_array($fields_)) |
| 248 | 249 | { |
| 249 | 250 | $fields = $fields_; |
| 250 | - } |
|
| 251 | - else |
|
| 251 | + } else |
|
| 252 | 252 | { |
| 253 | 253 | $args = array_keys($this->_filters); |
| 254 | 254 | $fields = (array) Context::getRequestVars(); |
@@ -281,13 +281,11 @@ discard block |
||
| 281 | 281 | if($key{0} == '^') |
| 282 | 282 | { |
| 283 | 283 | $names = preg_grep('/^' . preg_quote(substr($key, 1)) . '/', $field_names); |
| 284 | - } |
|
| 285 | - elseif(substr($key, -2) == '[]') |
|
| 284 | + } elseif(substr($key, -2) == '[]') |
|
| 286 | 285 | { |
| 287 | 286 | $filters[substr($key, 0, -2)] = $filter; |
| 288 | 287 | unset($filters[$key]); |
| 289 | - } |
|
| 290 | - else |
|
| 288 | + } else |
|
| 291 | 289 | { |
| 292 | 290 | $filters[$key] = $filter; |
| 293 | 291 | } |
@@ -313,8 +311,7 @@ discard block |
||
| 313 | 311 | { |
| 314 | 312 | $exists = array_key_exists($matches[1], $fields); |
| 315 | 313 | $value = $exists ? $fields[$matches[1]][$matches[2]] : NULL; |
| 316 | - } |
|
| 317 | - else |
|
| 314 | + } else |
|
| 318 | 315 | { |
| 319 | 316 | $exists = array_key_exists($key, $fields); |
| 320 | 317 | $value = $exists ? $fields[$fname] : NULL; |
@@ -325,8 +322,7 @@ discard block |
||
| 325 | 322 | if(!isset($value[tmp_name])) |
| 326 | 323 | { |
| 327 | 324 | $value = implode('', $value); |
| 328 | - } |
|
| 329 | - else |
|
| 325 | + } else |
|
| 330 | 326 | { |
| 331 | 327 | $value = $value['name']; |
| 332 | 328 | } |
@@ -356,8 +352,7 @@ discard block |
||
| 356 | 352 | if(is_null($fields_)) |
| 357 | 353 | { |
| 358 | 354 | Context::set($fname, $value); |
| 359 | - } |
|
| 360 | - else |
|
| 355 | + } else |
|
| 361 | 356 | { |
| 362 | 357 | $fields_[$fname] = $value; |
| 363 | 358 | } |
@@ -464,8 +459,7 @@ discard block |
||
| 464 | 459 | if(isset($this->_message[$msg])) |
| 465 | 460 | { |
| 466 | 461 | $msg = $this->_message[$msg]; |
| 467 | - } |
|
| 468 | - else |
|
| 462 | + } else |
|
| 469 | 463 | { |
| 470 | 464 | $lang_filter = Context::getLang('filter'); |
| 471 | 465 | $msg = isset($lang_filter->{$msg}) ? $lang_filter->{$msg} : $lang_filter->invalid; |
@@ -474,8 +468,7 @@ discard block |
||
| 474 | 468 | if(isset($this->_fieldNames[$field])) |
| 475 | 469 | { |
| 476 | 470 | $fieldName = $this->_fieldNames[$field]; |
| 477 | - } |
|
| 478 | - else |
|
| 471 | + } else |
|
| 479 | 472 | { |
| 480 | 473 | $fieldName = Context::getLang($field); |
| 481 | 474 | } |
@@ -507,8 +500,7 @@ discard block |
||
| 507 | 500 | if(is_array($name)) |
| 508 | 501 | { |
| 509 | 502 | $args = $name; |
| 510 | - } |
|
| 511 | - else |
|
| 503 | + } else |
|
| 512 | 504 | { |
| 513 | 505 | $args = array($name => $rule); |
| 514 | 506 | } |
@@ -555,8 +547,7 @@ discard block |
||
| 555 | 547 | if(is_array($name)) |
| 556 | 548 | { |
| 557 | 549 | $args = $name; |
| 558 | - } |
|
| 559 | - else |
|
| 550 | + } else |
|
| 560 | 551 | { |
| 561 | 552 | $args = array($name => $filter); |
| 562 | 553 | } |
@@ -577,8 +568,7 @@ discard block |
||
| 577 | 568 | { |
| 578 | 569 | $filter['if'] = array($filter['if']); |
| 579 | 570 | } |
| 580 | - } |
|
| 581 | - else |
|
| 571 | + } else |
|
| 582 | 572 | { |
| 583 | 573 | unset($filter['if']); |
| 584 | 574 | } |
@@ -753,8 +743,7 @@ discard block |
||
| 753 | 743 | { |
| 754 | 744 | $field_lang = addslashes($filter['title']); |
| 755 | 745 | $messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);"; |
| 756 | - } |
|
| 757 | - elseif(isset($lang->{$name})) |
|
| 746 | + } elseif(isset($lang->{$name})) |
|
| 758 | 747 | { |
| 759 | 748 | $field_lang = addslashes($lang->{$name}); |
| 760 | 749 | $messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);"; |
@@ -81,7 +81,7 @@ discard block |
||
| 81 | 81 | $this->_filters = array(); |
| 82 | 82 | $this->_xml_ruleset = NULL; |
| 83 | 83 | |
| 84 | - if($xml_path) |
|
| 84 | + if ($xml_path) |
|
| 85 | 85 | $this->load($xml_path); |
| 86 | 86 | |
| 87 | 87 | // predefined rules |
@@ -96,7 +96,7 @@ discard block |
||
| 96 | 96 | )); |
| 97 | 97 | |
| 98 | 98 | $this->_has_mb_func = is_callable('mb_strlen'); |
| 99 | - $this->setCacheDir(_XE_PATH_ . 'files/cache'); |
|
| 99 | + $this->setCacheDir(_XE_PATH_.'files/cache'); |
|
| 100 | 100 | } |
| 101 | 101 | |
| 102 | 102 | /** |
@@ -119,32 +119,32 @@ discard block |
||
| 119 | 119 | $this->_xml_ruleset = NULL; |
| 120 | 120 | |
| 121 | 121 | $xml_path = realpath($xml_path); |
| 122 | - if(!is_readable($xml_path)) |
|
| 122 | + if (!is_readable($xml_path)) |
|
| 123 | 123 | { |
| 124 | 124 | return FALSE; |
| 125 | 125 | } |
| 126 | 126 | |
| 127 | 127 | $parser = new XmlParser(); |
| 128 | 128 | $xml = $parser->loadXmlFile($xml_path); |
| 129 | - if(!isset($xml->ruleset) || !isset($xml->ruleset->fields) || !isset($xml->ruleset->fields->field)) |
|
| 129 | + if (!isset($xml->ruleset) || !isset($xml->ruleset->fields) || !isset($xml->ruleset->fields->field)) |
|
| 130 | 130 | { |
| 131 | 131 | return FALSE; |
| 132 | 132 | } |
| 133 | 133 | |
| 134 | 134 | // custom rules |
| 135 | - if(isset($xml->ruleset->customrules) && isset($xml->ruleset->customrules->rule)) |
|
| 135 | + if (isset($xml->ruleset->customrules) && isset($xml->ruleset->customrules->rule)) |
|
| 136 | 136 | { |
| 137 | 137 | $customrules = $xml->ruleset->customrules->rule; |
| 138 | - if(!is_array($customrules)) |
|
| 138 | + if (!is_array($customrules)) |
|
| 139 | 139 | { |
| 140 | 140 | $customrules = array($customrules); |
| 141 | 141 | } |
| 142 | 142 | |
| 143 | 143 | $rules = array(); |
| 144 | 144 | $messages = array(); |
| 145 | - foreach($customrules as $rule) |
|
| 145 | + foreach ($customrules as $rule) |
|
| 146 | 146 | { |
| 147 | - if(!isset($rule->attrs) || !isset($rule->attrs->name)) |
|
| 147 | + if (!isset($rule->attrs) || !isset($rule->attrs->name)) |
|
| 148 | 148 | { |
| 149 | 149 | continue; |
| 150 | 150 | } |
@@ -156,12 +156,12 @@ discard block |
||
| 156 | 156 | unset($rule['name']); |
| 157 | 157 | |
| 158 | 158 | $rules[$name] = $rule; |
| 159 | - if(isset($message)) |
|
| 159 | + if (isset($message)) |
|
| 160 | 160 | { |
| 161 | - $messages['invalid_' . $name] = $message; |
|
| 161 | + $messages['invalid_'.$name] = $message; |
|
| 162 | 162 | } |
| 163 | 163 | } |
| 164 | - if(count($rules)) |
|
| 164 | + if (count($rules)) |
|
| 165 | 165 | { |
| 166 | 166 | $this->addRule($rules); |
| 167 | 167 | } |
@@ -169,19 +169,19 @@ discard block |
||
| 169 | 169 | |
| 170 | 170 | // filters |
| 171 | 171 | $fields = $xml->ruleset->fields->field; |
| 172 | - if(!is_array($fields)) |
|
| 172 | + if (!is_array($fields)) |
|
| 173 | 173 | { |
| 174 | 174 | $fields = array($fields); |
| 175 | 175 | } |
| 176 | 176 | |
| 177 | 177 | $filters = array(); |
| 178 | 178 | $fieldsNames = array(); |
| 179 | - foreach($fields as $field) |
|
| 179 | + foreach ($fields as $field) |
|
| 180 | 180 | { |
| 181 | 181 | $name = ''; |
| 182 | 182 | $filter = array(); |
| 183 | 183 | |
| 184 | - if(!isset($field->attrs) || !isset($field->attrs->name)) |
|
| 184 | + if (!isset($field->attrs) || !isset($field->attrs->name)) |
|
| 185 | 185 | { |
| 186 | 186 | continue; |
| 187 | 187 | } |
@@ -191,7 +191,7 @@ discard block |
||
| 191 | 191 | $filter['title'] = $title; |
| 192 | 192 | |
| 193 | 193 | $name = $filter['name']; |
| 194 | - if(isset($title)) |
|
| 194 | + if (isset($title)) |
|
| 195 | 195 | { |
| 196 | 196 | $fieldsNames[$name] = $title; |
| 197 | 197 | } |
@@ -199,14 +199,14 @@ discard block |
||
| 199 | 199 | unset($filter['name']); |
| 200 | 200 | |
| 201 | 201 | // conditional statement |
| 202 | - if(isset($field->if)) |
|
| 202 | + if (isset($field->if)) |
|
| 203 | 203 | { |
| 204 | 204 | $if = $field->if; |
| 205 | - if(!is_array($if)) |
|
| 205 | + if (!is_array($if)) |
|
| 206 | 206 | { |
| 207 | 207 | $if = array($if); |
| 208 | 208 | } |
| 209 | - foreach($if as $idx => $cond) |
|
| 209 | + foreach ($if as $idx => $cond) |
|
| 210 | 210 | { |
| 211 | 211 | $if[$idx] = (array) $cond->attrs; |
| 212 | 212 | } |
@@ -232,7 +232,7 @@ discard block |
||
| 232 | 232 | */ |
| 233 | 233 | function setCacheDir($cache_dir) |
| 234 | 234 | { |
| 235 | - if(is_dir($cache_dir)) |
|
| 235 | + if (is_dir($cache_dir)) |
|
| 236 | 236 | { |
| 237 | 237 | $this->_cache_dir = preg_replace('@/$@', '', $cache_dir); |
| 238 | 238 | } |
@@ -245,7 +245,7 @@ discard block |
||
| 245 | 245 | */ |
| 246 | 246 | function validate($fields_ = null) |
| 247 | 247 | { |
| 248 | - if(is_array($fields_)) |
|
| 248 | + if (is_array($fields_)) |
|
| 249 | 249 | { |
| 250 | 250 | $fields = $fields_; |
| 251 | 251 | } |
@@ -255,7 +255,7 @@ discard block |
||
| 255 | 255 | $fields = (array) Context::getRequestVars(); |
| 256 | 256 | } |
| 257 | 257 | |
| 258 | - if(!is_array($fields)) |
|
| 258 | + if (!is_array($fields)) |
|
| 259 | 259 | { |
| 260 | 260 | return TRUE; |
| 261 | 261 | } |
@@ -276,14 +276,14 @@ discard block |
||
| 276 | 276 | $filters = array(); |
| 277 | 277 | |
| 278 | 278 | // get field names matching patterns |
| 279 | - foreach($this->_filters as $key => $filter) |
|
| 279 | + foreach ($this->_filters as $key => $filter) |
|
| 280 | 280 | { |
| 281 | 281 | $names = array(); |
| 282 | - if($key{0} == '^') |
|
| 282 | + if ($key{0} == '^') |
|
| 283 | 283 | { |
| 284 | - $names = preg_grep('/^' . preg_quote(substr($key, 1)) . '/', $field_names); |
|
| 284 | + $names = preg_grep('/^'.preg_quote(substr($key, 1)).'/', $field_names); |
|
| 285 | 285 | } |
| 286 | - elseif(substr($key, -2) == '[]') |
|
| 286 | + elseif (substr($key, -2) == '[]') |
|
| 287 | 287 | { |
| 288 | 288 | $filters[substr($key, 0, -2)] = $filter; |
| 289 | 289 | unset($filters[$key]); |
@@ -293,24 +293,24 @@ discard block |
||
| 293 | 293 | $filters[$key] = $filter; |
| 294 | 294 | } |
| 295 | 295 | |
| 296 | - if(!count($names)) |
|
| 296 | + if (!count($names)) |
|
| 297 | 297 | { |
| 298 | 298 | continue; |
| 299 | 299 | } |
| 300 | 300 | |
| 301 | - foreach($names as $name) |
|
| 301 | + foreach ($names as $name) |
|
| 302 | 302 | { |
| 303 | 303 | $filters[$name] = $filter; |
| 304 | 304 | } |
| 305 | 305 | unset($filters[$key]); |
| 306 | 306 | } |
| 307 | 307 | |
| 308 | - foreach($filters as $key => $filter) |
|
| 308 | + foreach ($filters as $key => $filter) |
|
| 309 | 309 | { |
| 310 | 310 | $fname = preg_replace('/\[\]$/', '', $key); |
| 311 | 311 | $filter = array_merge($filter_default, $filter); |
| 312 | 312 | |
| 313 | - if(preg_match("/(^[a-z_]*)[\[](?:\'|\")?([a-z_]*)(?:\'|\")?[\]]$/i", $key, $matches)) |
|
| 313 | + if (preg_match("/(^[a-z_]*)[\[](?:\'|\")?([a-z_]*)(?:\'|\")?[\]]$/i", $key, $matches)) |
|
| 314 | 314 | { |
| 315 | 315 | $exists = array_key_exists($matches[1], $fields); |
| 316 | 316 | $value = $exists ? $fields[$matches[1]][$matches[2]] : NULL; |
@@ -321,9 +321,9 @@ discard block |
||
| 321 | 321 | $value = $exists ? $fields[$fname] : NULL; |
| 322 | 322 | } |
| 323 | 323 | |
| 324 | - if(is_array($value)) |
|
| 324 | + if (is_array($value)) |
|
| 325 | 325 | { |
| 326 | - if(!isset($value[tmp_name])) |
|
| 326 | + if (!isset($value[tmp_name])) |
|
| 327 | 327 | { |
| 328 | 328 | $value = implode('', $value); |
| 329 | 329 | } |
@@ -334,9 +334,9 @@ discard block |
||
| 334 | 334 | } |
| 335 | 335 | |
| 336 | 336 | // conditional statement |
| 337 | - foreach($filter['if'] as $cond) |
|
| 337 | + foreach ($filter['if'] as $cond) |
|
| 338 | 338 | { |
| 339 | - if(!isset($cond['test']) || !isset($cond['attr'])) |
|
| 339 | + if (!isset($cond['test']) || !isset($cond['attr'])) |
|
| 340 | 340 | { |
| 341 | 341 | continue; |
| 342 | 342 | } |
@@ -344,17 +344,17 @@ discard block |
||
| 344 | 344 | $func_body = preg_replace('/\\$(\w+)/', '$c[\'$1\']', $cond['test']); |
| 345 | 345 | $func = create_function('$c', "return !!({$func_body});"); |
| 346 | 346 | |
| 347 | - if($func($fields)) |
|
| 347 | + if ($func($fields)) |
|
| 348 | 348 | { |
| 349 | 349 | $filter[$cond['attr']] = $cond['value']; |
| 350 | 350 | } |
| 351 | 351 | } |
| 352 | 352 | |
| 353 | 353 | // attr : default |
| 354 | - if(!$value && strlen($default = trim($filter['default']))) |
|
| 354 | + if (!$value && strlen($default = trim($filter['default']))) |
|
| 355 | 355 | { |
| 356 | 356 | $value = $default; |
| 357 | - if(is_null($fields_)) |
|
| 357 | + if (is_null($fields_)) |
|
| 358 | 358 | { |
| 359 | 359 | Context::set($fname, $value); |
| 360 | 360 | } |
@@ -366,25 +366,25 @@ discard block |
||
| 366 | 366 | $value_len = strlen($value); |
| 367 | 367 | |
| 368 | 368 | // attr : modifier |
| 369 | - if(is_string($modifiers = $filter['modifiers'])) |
|
| 369 | + if (is_string($modifiers = $filter['modifiers'])) |
|
| 370 | 370 | { |
| 371 | 371 | $modifiers = explode(',', trim($modifiers)); |
| 372 | 372 | } |
| 373 | 373 | |
| 374 | 374 | // attr : required |
| 375 | - if($filter['required'] === 'true' && !$value_len) |
|
| 375 | + if ($filter['required'] === 'true' && !$value_len) |
|
| 376 | 376 | { |
| 377 | 377 | return $this->error($key, 'isnull'); |
| 378 | 378 | } |
| 379 | 379 | |
| 380 | 380 | // if the field wasn't passed, ignore this value |
| 381 | - if(!$exists && !$value_len) |
|
| 381 | + if (!$exists && !$value_len) |
|
| 382 | 382 | { |
| 383 | 383 | continue; |
| 384 | 384 | } |
| 385 | 385 | |
| 386 | 386 | // attr : length |
| 387 | - if($length = $filter['length']) |
|
| 387 | + if ($length = $filter['length']) |
|
| 388 | 388 | { |
| 389 | 389 | list($min, $max) = explode(':', trim($length)); |
| 390 | 390 | $is_min_b = (substr($min, -1) === 'b'); |
@@ -392,41 +392,41 @@ discard block |
||
| 392 | 392 | list($min, $max) = array((int) $min, (int) $max); |
| 393 | 393 | |
| 394 | 394 | $strbytes = strlen($value); |
| 395 | - if(!$is_min_b || !$is_max_b) |
|
| 395 | + if (!$is_min_b || !$is_max_b) |
|
| 396 | 396 | { |
| 397 | 397 | $strlength = $this->_has_mb_func ? mb_strlen($value, 'utf-8') : $this->mbStrLen($value); |
| 398 | 398 | } |
| 399 | 399 | |
| 400 | - if(($min && $min > ($is_min_b ? $strbytes : $strlength)) || ($max && $max < ($is_max_b ? $strbytes : $strlength))) |
|
| 400 | + if (($min && $min > ($is_min_b ? $strbytes : $strlength)) || ($max && $max < ($is_max_b ? $strbytes : $strlength))) |
|
| 401 | 401 | { |
| 402 | 402 | return $this->error($key, 'outofrange'); |
| 403 | 403 | } |
| 404 | 404 | } |
| 405 | 405 | |
| 406 | 406 | // equalto |
| 407 | - if($equalto = $filter['equalto']) |
|
| 407 | + if ($equalto = $filter['equalto']) |
|
| 408 | 408 | { |
| 409 | - if(!array_key_exists($equalto, $fields) || trim($fields[$equalto]) !== $value) |
|
| 409 | + if (!array_key_exists($equalto, $fields) || trim($fields[$equalto]) !== $value) |
|
| 410 | 410 | { |
| 411 | 411 | return $this->error($key, 'equalto'); |
| 412 | 412 | } |
| 413 | 413 | } |
| 414 | 414 | |
| 415 | 415 | // rules |
| 416 | - if($rules = $filter['rule']) |
|
| 416 | + if ($rules = $filter['rule']) |
|
| 417 | 417 | { |
| 418 | 418 | $rules = explode(',', $rules); |
| 419 | - foreach($rules as $rule) |
|
| 419 | + foreach ($rules as $rule) |
|
| 420 | 420 | { |
| 421 | 421 | $result = $this->applyRule($rule, $value); |
| 422 | 422 | // apply the 'not' modifier |
| 423 | - if(in_array('not', $modifiers)) |
|
| 423 | + if (in_array('not', $modifiers)) |
|
| 424 | 424 | { |
| 425 | 425 | $result = !$result; |
| 426 | 426 | } |
| 427 | - if(!$result) |
|
| 427 | + if (!$result) |
|
| 428 | 428 | { |
| 429 | - return $this->error($key, 'invalid_' . $rule); |
|
| 429 | + return $this->error($key, 'invalid_'.$rule); |
|
| 430 | 430 | } |
| 431 | 431 | } |
| 432 | 432 | } |
@@ -442,12 +442,12 @@ discard block |
||
| 442 | 442 | */ |
| 443 | 443 | function arrayTrim($array) |
| 444 | 444 | { |
| 445 | - if(!is_array($array)) |
|
| 445 | + if (!is_array($array)) |
|
| 446 | 446 | { |
| 447 | 447 | return trim($array); |
| 448 | 448 | } |
| 449 | 449 | |
| 450 | - foreach($array as $key => $value) |
|
| 450 | + foreach ($array as $key => $value) |
|
| 451 | 451 | { |
| 452 | 452 | $array[$key] = $this->arrayTrim($value); |
| 453 | 453 | } |
@@ -462,7 +462,7 @@ discard block |
||
| 462 | 462 | */ |
| 463 | 463 | function error($field, $msg) |
| 464 | 464 | { |
| 465 | - if(isset($this->_message[$msg])) |
|
| 465 | + if (isset($this->_message[$msg])) |
|
| 466 | 466 | { |
| 467 | 467 | $msg = $this->_message[$msg]; |
| 468 | 468 | } |
@@ -472,7 +472,7 @@ discard block |
||
| 472 | 472 | $msg = isset($lang_filter->{$msg}) ? $lang_filter->{$msg} : $lang_filter->invalid; |
| 473 | 473 | } |
| 474 | 474 | |
| 475 | - if(isset($this->_fieldNames[$field])) |
|
| 475 | + if (isset($this->_fieldNames[$field])) |
|
| 476 | 476 | { |
| 477 | 477 | $fieldName = $this->_fieldNames[$field]; |
| 478 | 478 | } |
@@ -505,7 +505,7 @@ discard block |
||
| 505 | 505 | */ |
| 506 | 506 | function addRule($name, $rule = '') |
| 507 | 507 | { |
| 508 | - if(is_array($name)) |
|
| 508 | + if (is_array($name)) |
|
| 509 | 509 | { |
| 510 | 510 | $args = $name; |
| 511 | 511 | } |
@@ -514,18 +514,18 @@ discard block |
||
| 514 | 514 | $args = array($name => $rule); |
| 515 | 515 | } |
| 516 | 516 | |
| 517 | - foreach($args as $name => $rule) |
|
| 517 | + foreach ($args as $name => $rule) |
|
| 518 | 518 | { |
| 519 | - if(!$rule) |
|
| 519 | + if (!$rule) |
|
| 520 | 520 | { |
| 521 | 521 | continue; |
| 522 | 522 | } |
| 523 | - if(is_string($rule)) |
|
| 523 | + if (is_string($rule)) |
|
| 524 | 524 | { |
| 525 | 525 | $rule = array('type' => 'regex', 'test' => $rule); |
| 526 | 526 | } |
| 527 | 527 | |
| 528 | - if($rule['type'] == 'enum') |
|
| 528 | + if ($rule['type'] == 'enum') |
|
| 529 | 529 | { |
| 530 | 530 | $delim = isset($rule['delim']) ? $rule['delim'] : ','; |
| 531 | 531 | $rule['test'] = explode($delim, $rule['test']); |
@@ -553,7 +553,7 @@ discard block |
||
| 553 | 553 | */ |
| 554 | 554 | function addFilter($name, $filter = '') |
| 555 | 555 | { |
| 556 | - if(is_array($name)) |
|
| 556 | + if (is_array($name)) |
|
| 557 | 557 | { |
| 558 | 558 | $args = $name; |
| 559 | 559 | } |
@@ -562,19 +562,19 @@ discard block |
||
| 562 | 562 | $args = array($name => $filter); |
| 563 | 563 | } |
| 564 | 564 | |
| 565 | - foreach($args as $name => $filter) |
|
| 565 | + foreach ($args as $name => $filter) |
|
| 566 | 566 | { |
| 567 | - if(!$filter) |
|
| 567 | + if (!$filter) |
|
| 568 | 568 | { |
| 569 | 569 | continue; |
| 570 | 570 | } |
| 571 | 571 | |
| 572 | - if(isset($filter['if'])) |
|
| 572 | + if (isset($filter['if'])) |
|
| 573 | 573 | { |
| 574 | - if(is_array($filter['if']) && count($filter['if'])) |
|
| 574 | + if (is_array($filter['if']) && count($filter['if'])) |
|
| 575 | 575 | { |
| 576 | 576 | $key = key($filter['if']); |
| 577 | - if(!is_int($key)) |
|
| 577 | + if (!is_int($key)) |
|
| 578 | 578 | { |
| 579 | 579 | $filter['if'] = array($filter['if']); |
| 580 | 580 | } |
@@ -609,21 +609,21 @@ discard block |
||
| 609 | 609 | { |
| 610 | 610 | $rule = $this->_rules[$name]; |
| 611 | 611 | |
| 612 | - if(is_array($value) && isset($value['tmp_name'])) |
|
| 612 | + if (is_array($value) && isset($value['tmp_name'])) |
|
| 613 | 613 | { |
| 614 | 614 | $value = $value['name']; |
| 615 | 615 | } |
| 616 | 616 | |
| 617 | - switch($rule['type']) |
|
| 617 | + switch ($rule['type']) |
|
| 618 | 618 | { |
| 619 | 619 | case 'regex': |
| 620 | 620 | return (preg_match($rule['test'], $value) > 0); |
| 621 | 621 | case 'enum': |
| 622 | 622 | return in_array($value, $rule['test']); |
| 623 | 623 | case 'expr': |
| 624 | - if(!$rule['func_test']) |
|
| 624 | + if (!$rule['func_test']) |
|
| 625 | 625 | { |
| 626 | - $rule['func_test'] = create_function('$a', 'return (' . preg_replace('/\$\$/', '$a', html_entity_decode($rule['test'])) . ');'); |
|
| 626 | + $rule['func_test'] = create_function('$a', 'return ('.preg_replace('/\$\$/', '$a', html_entity_decode($rule['test'])).');'); |
|
| 627 | 627 | } |
| 628 | 628 | return $rule['func_test']($value); |
| 629 | 629 | } |
@@ -639,7 +639,7 @@ discard block |
||
| 639 | 639 | function mbStrLen($str) |
| 640 | 640 | { |
| 641 | 641 | $arr = count_chars($str); |
| 642 | - for($i = 0x80; $i < 0xc0; $i++) |
|
| 642 | + for ($i = 0x80; $i < 0xc0; $i++) |
|
| 643 | 643 | { |
| 644 | 644 | unset($arr[$i]); |
| 645 | 645 | } |
@@ -652,17 +652,17 @@ discard block |
||
| 652 | 652 | */ |
| 653 | 653 | function getJsPath() |
| 654 | 654 | { |
| 655 | - if(!$this->_cache_dir) |
|
| 655 | + if (!$this->_cache_dir) |
|
| 656 | 656 | { |
| 657 | 657 | return FALSE; |
| 658 | 658 | } |
| 659 | 659 | |
| 660 | - $dir = $this->_cache_dir . '/ruleset'; |
|
| 661 | - if(!is_dir($dir) && !mkdir($dir)) |
|
| 660 | + $dir = $this->_cache_dir.'/ruleset'; |
|
| 661 | + if (!is_dir($dir) && !mkdir($dir)) |
|
| 662 | 662 | { |
| 663 | 663 | return FALSE; |
| 664 | 664 | } |
| 665 | - if(!$this->_xml_path) |
|
| 665 | + if (!$this->_xml_path) |
|
| 666 | 666 | { |
| 667 | 667 | return FALSE; |
| 668 | 668 | } |
@@ -671,14 +671,14 @@ discard block |
||
| 671 | 671 | $lang_type = class_exists('Context', false) ? Context::getLangType() : 'en'; |
| 672 | 672 | |
| 673 | 673 | // check the file |
| 674 | - $filepath = $dir . '/' . md5($this->_version . ' ' . $this->_xml_path) . ".{$lang_type}.js"; |
|
| 675 | - if(is_readable($filepath) && filemtime($filepath) > filemtime($this->_xml_path)) |
|
| 674 | + $filepath = $dir.'/'.md5($this->_version.' '.$this->_xml_path).".{$lang_type}.js"; |
|
| 675 | + if (is_readable($filepath) && filemtime($filepath) > filemtime($this->_xml_path)) |
|
| 676 | 676 | { |
| 677 | 677 | return $filepath; |
| 678 | 678 | } |
| 679 | 679 | |
| 680 | 680 | $content = $this->_compile2js(); |
| 681 | - if($content === FALSE) |
|
| 681 | + if ($content === FALSE) |
|
| 682 | 682 | { |
| 683 | 683 | return FALSE; |
| 684 | 684 | } |
@@ -699,9 +699,9 @@ discard block |
||
| 699 | 699 | $ruleset = basename($this->_xml_path, '.xml'); |
| 700 | 700 | $content = array(); |
| 701 | 701 | |
| 702 | - if(preg_match('@(^|/)files/ruleset/\w+\.xml$@i', $this->_xml_path)) |
|
| 702 | + if (preg_match('@(^|/)files/ruleset/\w+\.xml$@i', $this->_xml_path)) |
|
| 703 | 703 | { |
| 704 | - $ruleset = '@' . $ruleset; |
|
| 704 | + $ruleset = '@'.$ruleset; |
|
| 705 | 705 | } |
| 706 | 706 | |
| 707 | 707 | list($ruleset) = explode('.', $ruleset); |
@@ -711,22 +711,22 @@ discard block |
||
| 711 | 711 | |
| 712 | 712 | // custom rulesets |
| 713 | 713 | $addrules = array(); |
| 714 | - foreach($this->_rules as $name => $rule) |
|
| 714 | + foreach ($this->_rules as $name => $rule) |
|
| 715 | 715 | { |
| 716 | 716 | $name = strtolower($name); |
| 717 | 717 | |
| 718 | - if(in_array($name, array('email', 'userid', 'url', 'alpha', 'alpha_number', 'number', 'float'))) |
|
| 718 | + if (in_array($name, array('email', 'userid', 'url', 'alpha', 'alpha_number', 'number', 'float'))) |
|
| 719 | 719 | { |
| 720 | 720 | continue; |
| 721 | 721 | } |
| 722 | 722 | |
| 723 | - switch($rule['type']) |
|
| 723 | + switch ($rule['type']) |
|
| 724 | 724 | { |
| 725 | 725 | case 'regex': |
| 726 | 726 | $addrules[] = "v.cast('ADD_RULE', ['{$name}', {$rule['test']}]);"; |
| 727 | 727 | break; |
| 728 | 728 | case 'enum': |
| 729 | - $enums = '"' . implode('","', $rule['test']) . '"'; |
|
| 729 | + $enums = '"'.implode('","', $rule['test']).'"'; |
|
| 730 | 730 | $addrules[] = "v.cast('ADD_RULE', ['{$name}', function($$){ return ($.inArray($$,[{$enums}]) > -1); }]);"; |
| 731 | 731 | break; |
| 732 | 732 | case 'expr': |
@@ -735,7 +735,7 @@ discard block |
||
| 735 | 735 | } |
| 736 | 736 | |
| 737 | 737 | // if have a message, add message |
| 738 | - if(isset($rule['message'])) |
|
| 738 | + if (isset($rule['message'])) |
|
| 739 | 739 | { |
| 740 | 740 | $text = preg_replace('@\r?\n@', '\\n', addslashes($rule['message'])); |
| 741 | 741 | $addrules[] = "v.cast('ADD_MESSAGE',['invalid_{$name}','{$text}']);"; |
@@ -746,79 +746,79 @@ discard block |
||
| 746 | 746 | // filters |
| 747 | 747 | $content = array(); |
| 748 | 748 | $messages = array(); |
| 749 | - foreach($this->_filters as $name => $filter) |
|
| 749 | + foreach ($this->_filters as $name => $filter) |
|
| 750 | 750 | { |
| 751 | 751 | $field = array(); |
| 752 | 752 | |
| 753 | 753 | // form filed name |
| 754 | - if(isset($filter['title'])) |
|
| 754 | + if (isset($filter['title'])) |
|
| 755 | 755 | { |
| 756 | 756 | $field_lang = addslashes($filter['title']); |
| 757 | 757 | $messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);"; |
| 758 | 758 | } |
| 759 | - elseif(isset($lang->{$name})) |
|
| 759 | + elseif (isset($lang->{$name})) |
|
| 760 | 760 | { |
| 761 | 761 | $field_lang = addslashes($lang->{$name}); |
| 762 | 762 | $messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);"; |
| 763 | 763 | } |
| 764 | 764 | |
| 765 | - if($filter['required'] == 'true') |
|
| 765 | + if ($filter['required'] == 'true') |
|
| 766 | 766 | { |
| 767 | 767 | $field[] = 'required:true'; |
| 768 | 768 | } |
| 769 | - if($filter['rule']) |
|
| 769 | + if ($filter['rule']) |
|
| 770 | 770 | { |
| 771 | - $field[] = "rule:'" . strtolower($filter['rule']) . "'"; |
|
| 771 | + $field[] = "rule:'".strtolower($filter['rule'])."'"; |
|
| 772 | 772 | } |
| 773 | - if($filter['default']) |
|
| 773 | + if ($filter['default']) |
|
| 774 | 774 | { |
| 775 | 775 | $field[] = "default:'{$filter['default']}'"; |
| 776 | 776 | } |
| 777 | - if($filter['modifier']) |
|
| 777 | + if ($filter['modifier']) |
|
| 778 | 778 | { |
| 779 | 779 | $field[] = "modifier:'{$filter['modifier']}'"; |
| 780 | 780 | } |
| 781 | - if($filter['length']) |
|
| 781 | + if ($filter['length']) |
|
| 782 | 782 | { |
| 783 | 783 | list($min, $max) = explode(':', $filter['length']); |
| 784 | - if($min) |
|
| 784 | + if ($min) |
|
| 785 | 785 | { |
| 786 | 786 | $field[] = "minlength:'{$min}'"; |
| 787 | 787 | } |
| 788 | - if($max) |
|
| 788 | + if ($max) |
|
| 789 | 789 | { |
| 790 | 790 | $field[] = "maxlength:'{$max}'"; |
| 791 | 791 | } |
| 792 | 792 | } |
| 793 | - if($filter['if']) |
|
| 793 | + if ($filter['if']) |
|
| 794 | 794 | { |
| 795 | 795 | $ifs = array(); |
| 796 | - if(!isset($filter['if'][0])) |
|
| 796 | + if (!isset($filter['if'][0])) |
|
| 797 | 797 | { |
| 798 | 798 | $filter['if'] = array($filter['if']); |
| 799 | 799 | } |
| 800 | - foreach($filter['if'] as $if) |
|
| 800 | + foreach ($filter['if'] as $if) |
|
| 801 | 801 | { |
| 802 | - $ifs[] = "{test:'" . addslashes($if['test']) . "', attr:'{$if['attr']}', value:'" . addslashes($if['value']) . "'}"; |
|
| 802 | + $ifs[] = "{test:'".addslashes($if['test'])."', attr:'{$if['attr']}', value:'".addslashes($if['value'])."'}"; |
|
| 803 | 803 | } |
| 804 | - $field[] = "'if':[" . implode(',', $ifs) . "]"; |
|
| 804 | + $field[] = "'if':[".implode(',', $ifs)."]"; |
|
| 805 | 805 | } |
| 806 | - if(count($field)) |
|
| 806 | + if (count($field)) |
|
| 807 | 807 | { |
| 808 | - $field = '{' . implode(',', $field) . '}'; |
|
| 808 | + $field = '{'.implode(',', $field).'}'; |
|
| 809 | 809 | $content[] = "'{$name}':{$field}"; |
| 810 | 810 | } |
| 811 | 811 | } |
| 812 | 812 | |
| 813 | - if(!$content) |
|
| 813 | + if (!$content) |
|
| 814 | 814 | { |
| 815 | 815 | return '/* Error : empty ruleset */'; |
| 816 | 816 | } |
| 817 | 817 | |
| 818 | 818 | // error messages |
| 819 | - foreach($lang->filter as $key => $text) |
|
| 819 | + foreach ($lang->filter as $key => $text) |
|
| 820 | 820 | { |
| 821 | - if($text) |
|
| 821 | + if ($text) |
|
| 822 | 822 | { |
| 823 | 823 | $text = preg_replace('@\r?\n@', '\\n', addslashes($text)); |
| 824 | 824 | $messages[] = "v.cast('ADD_MESSAGE',['{$key}','{$text}']);"; |
@@ -61,7 +61,7 @@ discard block |
||
| 61 | 61 | /** |
| 62 | 62 | * Character data handler |
| 63 | 63 | * Variable in the last element of this->output |
| 64 | - * @param resource $parse an instance of parser |
|
| 64 | + * @param resource $parser an instance of parser |
|
| 65 | 65 | * @param string $body a data to be added |
| 66 | 66 | * @return void |
| 67 | 67 | */ |
@@ -73,7 +73,7 @@ discard block |
||
| 73 | 73 | |
| 74 | 74 | /** |
| 75 | 75 | * End element handler |
| 76 | - * @param resource $parse an instance of parser |
|
| 76 | + * @param resource $parser an instance of parser |
|
| 77 | 77 | * @param string $node_name name of xml node |
| 78 | 78 | * @return void |
| 79 | 79 | */ |
@@ -32,7 +32,7 @@ discard block |
||
| 32 | 32 | xml_parse($oParser, $input); |
| 33 | 33 | xml_parser_free($oParser); |
| 34 | 34 | |
| 35 | - if(count($this->output) < 1) |
|
| 35 | + if (count($this->output) < 1) |
|
| 36 | 36 | { |
| 37 | 37 | return; |
| 38 | 38 | } |
@@ -84,9 +84,9 @@ discard block |
||
| 84 | 84 | $parent_obj = &$this->output[count($this->output) - 1]; |
| 85 | 85 | $tmp_obj = &$parent_obj->childNodes[$node_name]; |
| 86 | 86 | |
| 87 | - if($tmp_obj) |
|
| 87 | + if ($tmp_obj) |
|
| 88 | 88 | { |
| 89 | - if(is_array($tmp_obj)) |
|
| 89 | + if (is_array($tmp_obj)) |
|
| 90 | 90 | { |
| 91 | 91 | $tmp_obj[] = $cur_obj; |
| 92 | 92 | } |
@@ -89,13 +89,11 @@ |
||
| 89 | 89 | if(is_array($tmp_obj)) |
| 90 | 90 | { |
| 91 | 91 | $tmp_obj[] = $cur_obj; |
| 92 | - } |
|
| 93 | - else |
|
| 92 | + } else |
|
| 94 | 93 | { |
| 95 | 94 | $tmp_obj = array($tmp_obj, $cur_obj); |
| 96 | 95 | } |
| 97 | - } |
|
| 98 | - else |
|
| 96 | + } else |
|
| 99 | 97 | { |
| 100 | 98 | $tmp_obj = $cur_obj; |
| 101 | 99 | } |
