htmLawed extlib updated

This commit is contained in:
Mikael Nordfeldth 2013-09-24 01:37:38 +02:00
parent f268c3f877
commit f01c478aab
5 changed files with 4155 additions and 3676 deletions

View File

@ -1,9 +1,9 @@
<?php
/*
htmLawed 1.1.8.1, 16 July 2009
htmLawed 1.1.16, 29 August 2013
Copyright Santosh Patnaik
GPL v3 license
Dual licensed with LGPL 3 and GPL 2+
A PHP Labware internal utility; www.bioinformatics.org/phplabware/internal_utilities/htmLawed
See htmLawed_README.txt/htm
@ -51,7 +51,7 @@ foreach(explode(';', str_replace(array(' ', "\t", "\r", "\n"), '', $x)) as $v){
if($x2){$C['schemes'][$x] = array_flip(explode(',', $x2));}
}
if(!isset($C['schemes']['*'])){$C['schemes']['*'] = array('file'=>1, 'http'=>1, 'https'=>1,);}
if(!empty($C['safe']) && empty($C['schemes']['style'])){$C['schemes']['style'] = array('nil'=>1);}
if(!empty($C['safe']) && empty($C['schemes']['style'])){$C['schemes']['style'] = array('!'=>1);}
$C['abs_url'] = isset($C['abs_url']) ? $C['abs_url'] : 0;
if(!isset($C['base_url']) or !preg_match('`^[a-zA-Z\d.+\-]+://[^/]+/(.+?/)?$`', $C['base_url'])){
$C['base_url'] = $C['abs_url'] = 0;
@ -65,6 +65,7 @@ $C['cdata'] = isset($C['cdata']) ? $C['cdata'] : (empty($C['safe']) ? 3 : 0);
$C['clean_ms_char'] = empty($C['clean_ms_char']) ? 0 : $C['clean_ms_char'];
$C['comment'] = isset($C['comment']) ? $C['comment'] : (empty($C['safe']) ? 3 : 0);
$C['css_expression'] = empty($C['css_expression']) ? 0 : 1;
$C['direct_list_nest'] = empty($C['direct_list_nest']) ? 0 : 1;
$C['hexdec_entity'] = isset($C['hexdec_entity']) ? $C['hexdec_entity'] : 1;
$C['hook'] = (!empty($C['hook']) && function_exists($C['hook'])) ? $C['hook'] : 0;
$C['hook_tag'] = (!empty($C['hook_tag']) && function_exists($C['hook_tag'])) ? $C['hook_tag'] : 0;
@ -149,14 +150,15 @@ $cI = array('a'=>1, 'abbr'=>1, 'acronym'=>1, 'address'=>1, 'b'=>1, 'bdo'=>1, 'bi
$cN = array('a'=>array('a'=>1), 'button'=>array('a'=>1, 'button'=>1, 'fieldset'=>1, 'form'=>1, 'iframe'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'fieldset'=>array('fieldset'=>1), 'form'=>array('form'=>1), 'label'=>array('label'=>1), 'noscript'=>array('script'=>1), 'pre'=>array('big'=>1, 'font'=>1, 'img'=>1, 'object'=>1, 'script'=>1, 'small'=>1, 'sub'=>1, 'sup'=>1), 'rb'=>array('ruby'=>1), 'rt'=>array('ruby'=>1)); // Illegal
$cN2 = array_keys($cN);
$cR = array('blockquote'=>1, 'dir'=>1, 'dl'=>1, 'form'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'select'=>1, 'table'=>1, 'tbody'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1);
$cS = array('colgroup'=>array('col'=>1), 'dir'=>array('li'), 'dl'=>array('dd'=>1, 'dt'=>1), 'menu'=>array('li'=>1), 'ol'=>array('li'=>1), 'optgroup'=>array('option'=>1), 'option'=>array('#pcdata'=>1), 'rbc'=>array('rb'=>1), 'rp'=>array('#pcdata'=>1), 'rtc'=>array('rt'=>1), 'ruby'=>array('rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1), 'select'=>array('optgroup'=>1, 'option'=>1), 'script'=>array('#pcdata'=>1), 'table'=>array('caption'=>1, 'col'=>1, 'colgroup'=>1, 'tfoot'=>1, 'tbody'=>1, 'tr'=>1, 'thead'=>1), 'tbody'=>array('tr'=>1), 'tfoot'=>array('tr'=>1), 'textarea'=>array('#pcdata'=>1), 'thead'=>array('tr'=>1), 'tr'=>array('td'=>1, 'th'=>1), 'ul'=>array('li'=>1)); // Specific - immediate parent-child
$cS = array('colgroup'=>array('col'=>1), 'dir'=>array('li'=>1), 'dl'=>array('dd'=>1, 'dt'=>1), 'menu'=>array('li'=>1), 'ol'=>array('li'=>1), 'optgroup'=>array('option'=>1), 'option'=>array('#pcdata'=>1), 'rbc'=>array('rb'=>1), 'rp'=>array('#pcdata'=>1), 'rtc'=>array('rt'=>1), 'ruby'=>array('rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1), 'select'=>array('optgroup'=>1, 'option'=>1), 'script'=>array('#pcdata'=>1), 'table'=>array('caption'=>1, 'col'=>1, 'colgroup'=>1, 'tfoot'=>1, 'tbody'=>1, 'tr'=>1, 'thead'=>1), 'tbody'=>array('tr'=>1), 'tfoot'=>array('tr'=>1), 'textarea'=>array('#pcdata'=>1), 'thead'=>array('tr'=>1), 'tr'=>array('td'=>1, 'th'=>1), 'ul'=>array('li'=>1)); // Specific - immediate parent-child
if($GLOBALS['C']['direct_list_nest']){$cS['ol'] = $cS['ul'] += array('ol'=>1, 'ul'=>1);}
$cO = array('address'=>array('p'=>1), 'applet'=>array('param'=>1), 'blockquote'=>array('script'=>1), 'fieldset'=>array('legend'=>1, '#pcdata'=>1), 'form'=>array('script'=>1), 'map'=>array('area'=>1), 'object'=>array('param'=>1, 'embed'=>1)); // Other
$cT = array('colgroup'=>1, 'dd'=>1, 'dt'=>1, 'li'=>1, 'option'=>1, 'p'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1); // Omitable closing
// block/inline type; ins & del both type; #pcdata: text
$eB = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'del'=>1, 'dir'=>1, 'dl'=>1, 'div'=>1, 'fieldset'=>1, 'form'=>1, 'ins'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'isindex'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'p'=>1, 'pre'=>1, 'table'=>1, 'ul'=>1);
$eI = array('#pcdata'=>1, 'a'=>1, 'abbr'=>1, 'acronym'=>1, 'applet'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'br'=>1, 'button'=>1, 'cite'=>1, 'code'=>1, 'del'=>1, 'dfn'=>1, 'em'=>1, 'embed'=>1, 'font'=>1, 'i'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'ins'=>1, 'kbd'=>1, 'label'=>1, 'map'=>1, 'object'=>1, 'param'=>1, 'q'=>1, 'ruby'=>1, 's'=>1, 'samp'=>1, 'select'=>1, 'script'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1, 'tt'=>1, 'u'=>1, 'var'=>1);
$eI = array('#pcdata'=>1, 'a'=>1, 'abbr'=>1, 'acronym'=>1, 'applet'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'br'=>1, 'button'=>1, 'cite'=>1, 'code'=>1, 'del'=>1, 'dfn'=>1, 'em'=>1, 'embed'=>1, 'font'=>1, 'i'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'ins'=>1, 'kbd'=>1, 'label'=>1, 'map'=>1, 'object'=>1, 'q'=>1, 'ruby'=>1, 's'=>1, 'samp'=>1, 'select'=>1, 'script'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1, 'tt'=>1, 'u'=>1, 'var'=>1);
$eN = array('a'=>1, 'big'=>1, 'button'=>1, 'fieldset'=>1, 'font'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'label'=>1, 'object'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'small'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1); // Exclude from specific ele; $cN values
$eO = array('area'=>1, 'caption'=>1, 'col'=>1, 'colgroup'=>1, 'dd'=>1, 'dt'=>1, 'legend'=>1, 'li'=>1, 'optgroup'=>1, 'option'=>1, 'rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1, 'script'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'thead'=>1, 'th'=>1, 'tr'=>1); // Missing in $eB & $eI
$eO = array('area'=>1, 'caption'=>1, 'col'=>1, 'colgroup'=>1, 'dd'=>1, 'dt'=>1, 'legend'=>1, 'li'=>1, 'optgroup'=>1, 'option'=>1, 'param'=>1, 'rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1, 'script'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'thead'=>1, 'th'=>1, 'tr'=>1); // Missing in $eB & $eI
$eF = $eB + $eI;
// $in sets allowed child
@ -192,7 +194,10 @@ for($i=-1, $ci=count($t); ++$i<$ci;){
echo '&lt;', $s, $e, $a, '&gt;';
}
if(isset($x[0])){
if($do < 3 or isset($ok['#pcdata'])){echo $x;}
if(strlen(trim($x)) && (($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql))){
echo '<div>', $x, '</div>';
}
elseif($do < 3 or isset($ok['#pcdata'])){echo $x;}
elseif(strpos($x, "\x02\x04")){
foreach(preg_split('`(\x01\x02[^\x01\x02]+\x02\x01)`', $x, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY) as $v){
echo (substr($v, 0, 2) == "\x01\x02" ? $v : ($do > 4 ? preg_replace('`\S`', '', $v) : ''));
@ -200,7 +205,7 @@ for($i=-1, $ci=count($t); ++$i<$ci;){
}elseif($do > 4){echo preg_replace('`\S`', '', $x);}
}
// get markup
if(!preg_match('`^(/?)([a-zA-Z1-6]+)([^>]*)>(.*)`sm', $t[$i], $r)){$x = $t[$i]; continue;}
if(!preg_match('`^(/?)([a-z1-6]+)([^>]*)>(.*)`sm', $t[$i], $r)){$x = $t[$i]; continue;}
$s = null; $e = null; $a = null; $x = null; list($all, $s, $e, $a, $x) = $r;
// close tag
if($s){
@ -295,20 +300,14 @@ function hl_cmtcd($t){
// comment/CDATA sec handler
$t = $t[0];
global $C;
if($t[3] == '-'){
if(!$C['comment']){return $t;}
if($C['comment'] == 1){return '';}
if(!($v = $C[$n = $t[3] == '-' ? 'comment' : 'cdata'])){return $t;}
if($v == 1){return '';}
if($n == 'comment'){
if(substr(($t = preg_replace('`--+`', '-', substr($t, 4, -3))), -1) != ' '){$t .= ' ';}
$t = $C['comment'] == 2 ? str_replace(array('&', '<', '>'), array('&amp;', '&lt;', '&gt;'), $t) : $t;
$t = "\x01\x02\x04!--$t--\x05\x02\x01";
}else{ // CDATA
if(!$C['cdata']){return $t;}
if($C['cdata'] == 1){return '';}
$t = substr($t, 1, -1);
$t = $C['cdata'] == 2 ? str_replace(array('&', '<', '>'), array('&amp;', '&lt;', '&gt;'), $t) : $t;
$t = "\x01\x01\x04$t\x05\x01\x01";
}
return str_replace(array('&', '<', '>'), array("\x03", "\x04", "\x05"), $t);
else{$t = substr($t, 1, -1);}
$t = $v == 2 ? str_replace(array('&', '<', '>'), array('&amp;', '&lt;', '&gt;'), $t) : $t;
return str_replace(array('&', '<', '>'), array("\x03", "\x04", "\x05"), ($n == 'comment' ? "\x01\x02\x04!--$t--\x05\x02\x01" : "\x01\x01\x04$t\x05\x01\x01"));
// eof
}
@ -334,9 +333,11 @@ global $C;
$b = $a = '';
if($c == null){$c = 'style'; $b = $p[1]; $a = $p[3]; $p = trim($p[2]);}
$c = isset($C['schemes'][$c]) ? $C['schemes'][$c] : $C['schemes']['*'];
if(isset($c['*']) or !strcspn($p, '#?;')){return "{$b}{$p}{$a}";} // All ok, frag, query, param
if(preg_match('`^([a-z\d\-+.&#; ]+?)(:|&#(58|x3a);|%3a|\\\\0{0,4}3a).`i', $p, $m) && !isset($c[strtolower($m[1])])){ // Denied prot
return "{$b}denied:{$p}{$a}";
static $d = 'denied:';
if(isset($c['!']) && substr($p, 0, 7) != $d){$p = "$d$p";}
if(isset($c['*']) or !strcspn($p, '#?;') or (substr($p, 0, 7) == $d)){return "{$b}{$p}{$a}";} // All ok, frag, query, param
if(preg_match('`^([^:?[@!$()*,=/\'\]]+?)(:|&#(58|x3a);|%3a|\\\\0{0,4}3a).`i', $p, $m) && !isset($c[strtolower($m[1])])){ // Denied prot
return "{$b}{$d}{$p}{$a}";
}
if($C['abs_url']){
if($C['abs_url'] == -1 && strpos($p, $C['base_url']) === 0){ // Make url rel
@ -419,10 +420,7 @@ if(!preg_match('`^<(/?)([a-zA-Z][a-zA-Z1-6]*)([^>]*?)\s?>$`m', $t, $m)){
return (($C['keep_bad']%2) ? str_replace(array('<', '>'), array('&lt;', '&gt;'), $t) : '');
}
// attr string
$a = str_replace(array("\xad", "\n", "\r", "\t"), ' ', trim($m[3]));
if(strpos($a, '&') !== false){
str_replace(array('&#xad;', '&#173;', '&shy;'), ' ', $a);
}
$a = str_replace(array("\n", "\r", "\t"), ' ', trim($m[3]));
// tag transform
static $eD = array('applet'=>1, 'center'=>1, 'dir'=>1, 'embed'=>1, 'font'=>1, 'isindex'=>1, 'menu'=>1, 's'=>1, 'strike'=>1, 'u'=>1); // Deprecated
if($C['make_tag_strict'] && isset($eD[$e])){
@ -432,11 +430,11 @@ if($C['make_tag_strict'] && isset($eD[$e])){
// close tag
static $eE = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); // Empty ele
if(!empty($m[1])){
return (!isset($eE[$e]) ? "</$e>" : (($C['keep_bad'])%2 ? str_replace(array('<', '>'), array('&lt;', '&gt;'), $t) : ''));
return (!isset($eE[$e]) ? (empty($C['hook_tag']) ? "</$e>" : $C['hook_tag']($e)) : (($C['keep_bad'])%2 ? str_replace(array('<', '>'), array('&lt;', '&gt;'), $t) : ''));
}
// open tag & attr
static $aN = array('abbr'=>array('td'=>1, 'th'=>1), 'accept-charset'=>array('form'=>1), 'accept'=>array('form'=>1, 'input'=>1), 'accesskey'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'legend'=>1, 'textarea'=>1), 'action'=>array('form'=>1), 'align'=>array('caption'=>1, 'embed'=>1, 'applet'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'object'=>1, 'legend'=>1, 'table'=>1, 'hr'=>1, 'div'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'p'=>1, 'col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'alt'=>array('applet'=>1, 'area'=>1, 'img'=>1, 'input'=>1), 'archive'=>array('applet'=>1, 'object'=>1), 'axis'=>array('td'=>1, 'th'=>1), 'bgcolor'=>array('embed'=>1, 'table'=>1, 'tr'=>1, 'td'=>1, 'th'=>1), 'border'=>array('table'=>1, 'img'=>1, 'object'=>1), 'bordercolor'=>array('table'=>1, 'td'=>1, 'tr'=>1), 'cellpadding'=>array('table'=>1), 'cellspacing'=>array('table'=>1), 'char'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charoff'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charset'=>array('a'=>1, 'script'=>1), 'checked'=>array('input'=>1), 'cite'=>array('blockquote'=>1, 'q'=>1, 'del'=>1, 'ins'=>1), 'classid'=>array('object'=>1), 'clear'=>array('br'=>1), 'code'=>array('applet'=>1), 'codebase'=>array('object'=>1, 'applet'=>1), 'codetype'=>array('object'=>1), 'color'=>array('font'=>1), 'cols'=>array('textarea'=>1), 'colspan'=>array('td'=>1, 'th'=>1), 'compact'=>array('dir'=>1, 'dl'=>1, 'menu'=>1, 'ol'=>1, 'ul'=>1), 'coords'=>array('area'=>1, 'a'=>1), 'data'=>array('object'=>1), 'datetime'=>array('del'=>1, 'ins'=>1), 'declare'=>array('object'=>1), 'defer'=>array('script'=>1), 'dir'=>array('bdo'=>1), 'disabled'=>array('button'=>1, 'input'=>1, 'optgroup'=>1, 'option'=>1, 'select'=>1, 'textarea'=>1), 'enctype'=>array('form'=>1), 'face'=>array('font'=>1), 'for'=>array('label'=>1), 'frame'=>array('table'=>1), 'frameborder'=>array('iframe'=>1), 'headers'=>array('td'=>1, 'th'=>1), 'height'=>array('embed'=>1, 'iframe'=>1, 'td'=>1, 'th'=>1, 'img'=>1, 'object'=>1, 'applet'=>1), 'href'=>array('a'=>1, 'area'=>1), 'hreflang'=>array('a'=>1), 'hspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'ismap'=>array('img'=>1, 'input'=>1), 'label'=>array('option'=>1, 'optgroup'=>1), 'language'=>array('script'=>1), 'longdesc'=>array('img'=>1, 'iframe'=>1), 'marginheight'=>array('iframe'=>1), 'marginwidth'=>array('iframe'=>1), 'maxlength'=>array('input'=>1), 'method'=>array('form'=>1), 'model'=>array('embed'=>1), 'multiple'=>array('select'=>1), 'name'=>array('button'=>1, 'embed'=>1, 'textarea'=>1, 'applet'=>1, 'select'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'a'=>1, 'input'=>1, 'object'=>1, 'map'=>1, 'param'=>1), 'nohref'=>array('area'=>1), 'noshade'=>array('hr'=>1), 'nowrap'=>array('td'=>1, 'th'=>1), 'object'=>array('applet'=>1), 'onblur'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onchange'=>array('input'=>1, 'select'=>1, 'textarea'=>1), 'onfocus'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onreset'=>array('form'=>1), 'onselect'=>array('input'=>1, 'textarea'=>1), 'onsubmit'=>array('form'=>1), 'pluginspage'=>array('embed'=>1), 'pluginurl'=>array('embed'=>1), 'prompt'=>array('isindex'=>1), 'readonly'=>array('textarea'=>1, 'input'=>1), 'rel'=>array('a'=>1), 'rev'=>array('a'=>1), 'rows'=>array('textarea'=>1), 'rowspan'=>array('td'=>1, 'th'=>1), 'rules'=>array('table'=>1), 'scope'=>array('td'=>1, 'th'=>1), 'scrolling'=>array('iframe'=>1), 'selected'=>array('option'=>1), 'shape'=>array('area'=>1, 'a'=>1), 'size'=>array('hr'=>1, 'font'=>1, 'input'=>1, 'select'=>1), 'span'=>array('col'=>1, 'colgroup'=>1), 'src'=>array('embed'=>1, 'script'=>1, 'input'=>1, 'iframe'=>1, 'img'=>1), 'standby'=>array('object'=>1), 'start'=>array('ol'=>1), 'summary'=>array('table'=>1), 'tabindex'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'object'=>1, 'select'=>1, 'textarea'=>1), 'target'=>array('a'=>1, 'area'=>1, 'form'=>1), 'type'=>array('a'=>1, 'embed'=>1, 'object'=>1, 'param'=>1, 'script'=>1, 'input'=>1, 'li'=>1, 'ol'=>1, 'ul'=>1, 'button'=>1), 'usemap'=>array('img'=>1, 'input'=>1, 'object'=>1), 'valign'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'value'=>array('input'=>1, 'option'=>1, 'param'=>1, 'button'=>1, 'li'=>1), 'valuetype'=>array('param'=>1), 'vspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'width'=>array('embed'=>1, 'hr'=>1, 'iframe'=>1, 'img'=>1, 'object'=>1, 'table'=>1, 'td'=>1, 'th'=>1, 'applet'=>1, 'col'=>1, 'colgroup'=>1, 'pre'=>1), 'wmode'=>array('embed'=>1), 'xml:space'=>array('pre'=>1, 'script'=>1, 'style'=>1)); // Ele-specific
static $aN = array('abbr'=>array('td'=>1, 'th'=>1), 'accept-charset'=>array('form'=>1), 'accept'=>array('form'=>1, 'input'=>1), 'accesskey'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'legend'=>1, 'textarea'=>1), 'action'=>array('form'=>1), 'align'=>array('caption'=>1, 'embed'=>1, 'applet'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'object'=>1, 'legend'=>1, 'table'=>1, 'hr'=>1, 'div'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'p'=>1, 'col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'alt'=>array('applet'=>1, 'area'=>1, 'img'=>1, 'input'=>1), 'archive'=>array('applet'=>1, 'object'=>1), 'axis'=>array('td'=>1, 'th'=>1), 'bgcolor'=>array('embed'=>1, 'table'=>1, 'tr'=>1, 'td'=>1, 'th'=>1), 'border'=>array('table'=>1, 'img'=>1, 'object'=>1), 'bordercolor'=>array('table'=>1, 'td'=>1, 'tr'=>1), 'cellpadding'=>array('table'=>1), 'cellspacing'=>array('table'=>1), 'char'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charoff'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charset'=>array('a'=>1, 'script'=>1), 'checked'=>array('input'=>1), 'cite'=>array('blockquote'=>1, 'q'=>1, 'del'=>1, 'ins'=>1), 'classid'=>array('object'=>1), 'clear'=>array('br'=>1), 'code'=>array('applet'=>1), 'codebase'=>array('object'=>1, 'applet'=>1), 'codetype'=>array('object'=>1), 'color'=>array('font'=>1), 'cols'=>array('textarea'=>1), 'colspan'=>array('td'=>1, 'th'=>1), 'compact'=>array('dir'=>1, 'dl'=>1, 'menu'=>1, 'ol'=>1, 'ul'=>1), 'coords'=>array('area'=>1, 'a'=>1), 'data'=>array('object'=>1), 'datetime'=>array('del'=>1, 'ins'=>1), 'declare'=>array('object'=>1), 'defer'=>array('script'=>1), 'dir'=>array('bdo'=>1), 'disabled'=>array('button'=>1, 'input'=>1, 'optgroup'=>1, 'option'=>1, 'select'=>1, 'textarea'=>1), 'enctype'=>array('form'=>1), 'face'=>array('font'=>1), 'flashvars'=>array('embed'=>1), 'for'=>array('label'=>1), 'frame'=>array('table'=>1), 'frameborder'=>array('iframe'=>1), 'headers'=>array('td'=>1, 'th'=>1), 'height'=>array('embed'=>1, 'iframe'=>1, 'td'=>1, 'th'=>1, 'img'=>1, 'object'=>1, 'applet'=>1), 'href'=>array('a'=>1, 'area'=>1), 'hreflang'=>array('a'=>1), 'hspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'ismap'=>array('img'=>1, 'input'=>1), 'label'=>array('option'=>1, 'optgroup'=>1), 'language'=>array('script'=>1), 'longdesc'=>array('img'=>1, 'iframe'=>1), 'marginheight'=>array('iframe'=>1), 'marginwidth'=>array('iframe'=>1), 'maxlength'=>array('input'=>1), 'method'=>array('form'=>1), 'model'=>array('embed'=>1), 'multiple'=>array('select'=>1), 'name'=>array('button'=>1, 'embed'=>1, 'textarea'=>1, 'applet'=>1, 'select'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'a'=>1, 'input'=>1, 'object'=>1, 'map'=>1, 'param'=>1), 'nohref'=>array('area'=>1), 'noshade'=>array('hr'=>1), 'nowrap'=>array('td'=>1, 'th'=>1), 'object'=>array('applet'=>1), 'onblur'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onchange'=>array('input'=>1, 'select'=>1, 'textarea'=>1), 'onfocus'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onreset'=>array('form'=>1), 'onselect'=>array('input'=>1, 'textarea'=>1), 'onsubmit'=>array('form'=>1), 'pluginspage'=>array('embed'=>1), 'pluginurl'=>array('embed'=>1), 'prompt'=>array('isindex'=>1), 'readonly'=>array('textarea'=>1, 'input'=>1), 'rel'=>array('a'=>1), 'rev'=>array('a'=>1), 'rows'=>array('textarea'=>1), 'rowspan'=>array('td'=>1, 'th'=>1), 'rules'=>array('table'=>1), 'scope'=>array('td'=>1, 'th'=>1), 'scrolling'=>array('iframe'=>1), 'selected'=>array('option'=>1), 'shape'=>array('area'=>1, 'a'=>1), 'size'=>array('hr'=>1, 'font'=>1, 'input'=>1, 'select'=>1), 'span'=>array('col'=>1, 'colgroup'=>1), 'src'=>array('embed'=>1, 'script'=>1, 'input'=>1, 'iframe'=>1, 'img'=>1), 'standby'=>array('object'=>1), 'start'=>array('ol'=>1), 'summary'=>array('table'=>1), 'tabindex'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'object'=>1, 'select'=>1, 'textarea'=>1), 'target'=>array('a'=>1, 'area'=>1, 'form'=>1), 'type'=>array('a'=>1, 'embed'=>1, 'object'=>1, 'param'=>1, 'script'=>1, 'input'=>1, 'li'=>1, 'ol'=>1, 'ul'=>1, 'button'=>1), 'usemap'=>array('img'=>1, 'input'=>1, 'object'=>1), 'valign'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'value'=>array('input'=>1, 'option'=>1, 'param'=>1, 'button'=>1, 'li'=>1), 'valuetype'=>array('param'=>1), 'vspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'width'=>array('embed'=>1, 'hr'=>1, 'iframe'=>1, 'img'=>1, 'object'=>1, 'table'=>1, 'td'=>1, 'th'=>1, 'applet'=>1, 'col'=>1, 'colgroup'=>1, 'pre'=>1), 'wmode'=>array('embed'=>1), 'xml:space'=>array('pre'=>1, 'script'=>1, 'style'=>1)); // Ele-specific
static $aNE = array('checked'=>1, 'compact'=>1, 'declare'=>1, 'defer'=>1, 'disabled'=>1, 'ismap'=>1, 'multiple'=>1, 'nohref'=>1, 'noresize'=>1, 'noshade'=>1, 'nowrap'=>1, 'readonly'=>1, 'selected'=>1); // Empty
static $aNP = array('action'=>1, 'cite'=>1, 'classid'=>1, 'codebase'=>1, 'data'=>1, 'href'=>1, 'longdesc'=>1, 'model'=>1, 'pluginspage'=>1, 'pluginurl'=>1, 'usemap'=>1); // Need scheme check; excludes style, on* & src
static $aNU = array('class'=>array('param'=>1, 'script'=>1), 'dir'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'id'=>array('script'=>1), 'lang'=>array('applet'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'xml:lang'=>array('applet'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'onclick'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'ondblclick'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeydown'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeypress'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeyup'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmousedown'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmousemove'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseout'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseover'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseup'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'style'=>array('param'=>1, 'script'=>1), 'title'=>array('param'=>1, 'script'=>1)); // Univ & exceptions
@ -475,8 +473,8 @@ while(strlen($a)){
$aA[$nm] = '';
}
break; case 2: // Val
if(preg_match('`^"[^"]*"`', $a, $m) or preg_match("`^'[^']*'`", $a, $m) or preg_match("`^\s*[^\s\"']+`", $a, $m)){
$m = $m[0]; $w = 1; $mode = 0; $a = ltrim(substr_replace($a, '', 0, strlen($m)));
if(preg_match('`^((?:"[^"]*")|(?:\'[^\']*\')|(?:\s*[^\s"\']+))(.*)`', $a, $m)){
$a = ltrim($m[2]); $m = $m[1]; $w = 1; $mode = 0;
$aA[$nm] = trim(($m[0] == '"' or $m[0] == '\'') ? substr($m, 1, -1) : $m);
}
break;
@ -493,7 +491,7 @@ global $S;
$rl = isset($S[$e]) ? $S[$e] : array();
$a = array(); $nfr = 0;
foreach($aA as $k=>$v){
if(((isset($C['deny_attribute']['*']) ? isset($C['deny_attribute'][$k]) : !isset($C['deny_attribute'][$k])) or isset($rl[$k])) && ((!isset($rl['n'][$k]) && !isset($rl['n']['*'])) or isset($rl[$k])) && (isset($aN[$k][$e]) or (isset($aNU[$k]) && !isset($aNU[$k][$e])))){
if(((isset($C['deny_attribute']['*']) ? isset($C['deny_attribute'][$k]) : !isset($C['deny_attribute'][$k])) && (isset($aN[$k][$e]) or (isset($aNU[$k]) && !isset($aNU[$k][$e]))) && !isset($rl['n'][$k]) && !isset($rl['n']['*'])) or isset($rl[$k])){
if(isset($aNE[$k])){$v = $k;}
elseif(!empty($lcase) && (($e != 'button' or $e != 'input') or $k == 'type')){ // Rather loose but ?not cause issues
$v = (isset($aNL[($v2 = strtolower($v))])) ? $v2 : $v;
@ -503,9 +501,10 @@ foreach($aA as $k=>$v){
static $sC = array('&#x20;'=>' ', '&#32;'=>' ', '&#x45;'=>'e', '&#69;'=>'e', '&#x65;'=>'e', '&#101;'=>'e', '&#x58;'=>'x', '&#88;'=>'x', '&#x78;'=>'x', '&#120;'=>'x', '&#x50;'=>'p', '&#80;'=>'p', '&#x70;'=>'p', '&#112;'=>'p', '&#x53;'=>'s', '&#83;'=>'s', '&#x73;'=>'s', '&#115;'=>'s', '&#x49;'=>'i', '&#73;'=>'i', '&#x69;'=>'i', '&#105;'=>'i', '&#x4f;'=>'o', '&#79;'=>'o', '&#x6f;'=>'o', '&#111;'=>'o', '&#x4e;'=>'n', '&#78;'=>'n', '&#x6e;'=>'n', '&#110;'=>'n', '&#x55;'=>'u', '&#85;'=>'u', '&#x75;'=>'u', '&#117;'=>'u', '&#x52;'=>'r', '&#82;'=>'r', '&#x72;'=>'r', '&#114;'=>'r', '&#x4c;'=>'l', '&#76;'=>'l', '&#x6c;'=>'l', '&#108;'=>'l', '&#x28;'=>'(', '&#40;'=>'(', '&#x29;'=>')', '&#41;'=>')', '&#x20;'=>':', '&#32;'=>':', '&#x22;'=>'"', '&#34;'=>'"', '&#x27;'=>"'", '&#39;'=>"'", '&#x2f;'=>'/', '&#47;'=>'/', '&#x2a;'=>'*', '&#42;'=>'*', '&#x5c;'=>'\\', '&#92;'=>'\\');
$v = strtr($v, $sC);
}
$v = preg_replace_callback('`(url(?:\()(?: )*(?:\'|"|&(?:quot|apos);)?)(.+)((?:\'|"|&(?:quot|apos);)?(?: )*(?:\)))`iS', 'hl_prot', $v);
$v = preg_replace_callback('`(url(?:\()(?: )*(?:\'|"|&(?:quot|apos);)?)(.+?)((?:\'|"|&(?:quot|apos);)?(?: )*(?:\)))`iS', 'hl_prot', $v);
$v = !$C['css_expression'] ? preg_replace('`expression`i', ' ', preg_replace('`\\\\\S|(/|(%2f))(\*|(%2a))`i', ' ', $v)) : $v;
}elseif(isset($aNP[$k]) or strpos($k, 'src') !== false or $k[0] == 'o'){
$v = str_replace("\xad", ' ', (strpos($v, '&') !== false ? str_replace(array('&#xad;', '&#173;', '&shy;'), ' ', $v) : $v));
$v = hl_prot($v, $k);
if($k == 'href'){ // X-spam
if($C['anti_mail_spam'] && strpos($v, 'mailto:') === 0){
@ -626,7 +625,7 @@ if($e == 'u'){$e = 'span'; return 'text-decoration: underline;';}
static $fs = array('0'=>'xx-small', '1'=>'xx-small', '2'=>'small', '3'=>'medium', '4'=>'large', '5'=>'x-large', '6'=>'xx-large', '7'=>'300%', '-1'=>'smaller', '-2'=>'60%', '+1'=>'larger', '+2'=>'150%', '+3'=>'200%', '+4'=>'300%');
if($e == 'font'){
$a2 = '';
if(preg_match('`face\s*=\s*(\'|")([^=]+?)\\1`i', $a, $m) or preg_match('`face\s*=\s*([^"])(\S+)`i', $a, $m)){
if(preg_match('`face\s*=\s*(\'|")([^=]+?)\\1`i', $a, $m) or preg_match('`face\s*=(\s*)(\S+)`i', $a, $m)){
$a2 .= ' font-family: '. str_replace('"', '\'', trim($m[2])). ';';
}
if(preg_match('`color\s*=\s*(\'|")?(.+?)(\\1|\s|$)`i', $a, $m)){
@ -645,41 +644,50 @@ return '';
function hl_tidy($t, $w, $p){
// Tidy/compact HTM
if(strpos(' pre,script,textarea', "$p,")){return $t;}
$t = str_replace(' </', '</', preg_replace(array('`(<\w[^>]*(?<!/)>)\s+`', '`\s+`', '`(<\w[^>]*(?<!/)>) `'), array(' $1', ' ', '$1'), preg_replace_callback(array('`(<(!\[CDATA\[))(.+?)(\]\]>)`sm', '`(<(!--))(.+?)(-->)`sm', '`(<(pre|script|textarea).*?>)(.+?)(</\2>)`sm'), create_function('$m', 'return $m[1]. str_replace(array("<", ">", "\n", "\r", "\t", " "), array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), $m[3]). $m[4];'), $t)));
$t = preg_replace('`\s+`', ' ', preg_replace_callback(array('`(<(!\[CDATA\[))(.+?)(\]\]>)`sm', '`(<(!--))(.+?)(-->)`sm', '`(<(pre|script|textarea)[^>]*?>)(.+?)(</\2>)`sm'), create_function('$m', 'return $m[1]. str_replace(array("<", ">", "\n", "\r", "\t", " "), array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), $m[3]). $m[4];'), $t));
if(($w = strtolower($w)) == -1){
return str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), array('<', '>', "\n", "\r", "\t", ' '), $t);
}
$s = strpos(" $w", 't') ? "\t" : ' ';
$s = preg_match('`\d`', $w, $m) ? str_repeat($s, $m[0]) : str_repeat($s, ($s == "\t" ? 1 : 2));
$n = preg_match('`[ts]([1-9])`', $w, $m) ? $m[1] : 0;
$N = preg_match('`[ts]([1-9])`', $w, $m) ? $m[1] : 0;
$a = array('br'=>1);
$b = array('button'=>1, 'input'=>1, 'option'=>1);
$b = array('button'=>1, 'input'=>1, 'option'=>1, 'param'=>1);
$c = array('caption'=>1, 'dd'=>1, 'dt'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'isindex'=>1, 'label'=>1, 'legend'=>1, 'li'=>1, 'object'=>1, 'p'=>1, 'pre'=>1, 'td'=>1, 'textarea'=>1, 'th'=>1);
$d = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'colgroup'=>1, 'dir'=>1, 'div'=>1, 'dl'=>1, 'fieldset'=>1, 'form'=>1, 'hr'=>1, 'iframe'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'table'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1);
ob_start();
if(isset($d[$p])){echo str_repeat($s, ++$n);}
$t = explode('<', $t);
echo ltrim(array_shift($t));
for($i=-1, $j=count($t); ++$i<$j;){
$r = ''; list($e, $r) = explode('>', $t[$i]);
$x = $e[0] == '/' ? 0 : (substr($e, -1) == '/' ? 1 : ($e[0] != '!' ? 2 : -1));
$y = !$x ? ltrim($e, '/') : ($x > 0 ? substr($e, 0, strcspn($e, ' ')) : 0);
$e = "<$e>";
if(isset($d[$y])){
if(!$x){echo "\n", str_repeat($s, --$n), "$e\n", str_repeat($s, $n);}
else{echo "\n", str_repeat($s, $n), "$e\n", str_repeat($s, ($x != 1 ? ++$n : $n));}
echo ltrim($r); continue;
$d = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'colgroup'=>1, 'dir'=>1, 'div'=>1, 'dl'=>1, 'fieldset'=>1, 'form'=>1, 'hr'=>1, 'iframe'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'table'=>1, 'tbody'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1);
$T = explode('<', $t);
$X = 1;
while($X){
$n = $N;
$t = $T;
ob_start();
if(isset($d[$p])){echo str_repeat($s, ++$n);}
echo ltrim(array_shift($t));
for($i=-1, $j=count($t); ++$i<$j;){
$r = ''; list($e, $r) = explode('>', $t[$i]);
$x = $e[0] == '/' ? 0 : (substr($e, -1) == '/' ? 1 : ($e[0] != '!' ? 2 : -1));
$y = !$x ? ltrim($e, '/') : ($x > 0 ? substr($e, 0, strcspn($e, ' ')) : 0);
$e = "<$e>";
if(isset($d[$y])){
if(!$x){
if($n){echo "\n", str_repeat($s, --$n), "$e\n", str_repeat($s, $n);}
else{++$N; ob_end_clean(); continue 2;}
}
else{echo "\n", str_repeat($s, $n), "$e\n", str_repeat($s, ($x != 1 ? ++$n : $n));}
echo $r; continue;
}
$f = "\n". str_repeat($s, $n);
if(isset($c[$y])){
if(!$x){echo $e, $f, $r;}
else{echo $f, $e, $r;}
}elseif(isset($b[$y])){echo $f, $e, $r;
}elseif(isset($a[$y])){echo $e, $f, $r;
}elseif(!$y){echo $f, $e, $f, $r;
}else{echo $e, $r;}
}
$f = "\n". str_repeat($s, $n);
if(isset($c[$y])){
if(!$x){echo $e, $f, ltrim($r);}
else{echo $f, $e, $r;}
}elseif(isset($b[$y])){echo $f, $e, $r;
}elseif(isset($a[$y])){echo $e, $f, ltrim($r);
}elseif(!$y){echo $f, $e, $f, ltrim($r);
}else{echo $e, $r;}
$X = 0;
}
$t = preg_replace('`[\n]\s*?[\n]+`', "\n", ob_get_contents());
$t = str_replace(array("\n ", " \n"), "\n", preg_replace('`[\n]\s*?[\n]+`', "\n", ob_get_contents()));
ob_end_clean();
if(($l = strpos(" $w", 'r') ? (strpos(" $w", 'n') ? "\r\n" : "\r") : 0)){
$t = str_replace("\n", $l, $t);
@ -690,7 +698,7 @@ return str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), array(
function hl_version(){
// rel
return '1.1.8.1';
return '1.1.16';
// eof
}

View File

@ -1,10 +1,10 @@
<?php
/*
htmLawedTest.php, 16 July 2009
htmLawed 1.1.8.1, 16 July 2009
htmLawedTest.php, 28 May 2013
htmLawed 1.1.16, 29 August 2013
Copyright Santosh Patnaik
GPL v3 license
Dual licensed with LGPL 3 and GPL 2+
A PHP Labware internal utility - http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed
Test htmLawed; user provides text input; input and processed input are shown as highlighted code and rendered HTML; also shown are execution time and peak memory usage
@ -22,7 +22,7 @@ $_sid = 'sid'; // session name; alphanum.
$_slife = 30; // session life in min.
// errors
error_reporting(E_ALL | (defined('E_STRICT') ? E_STRICT : 1));
error_reporting(E_ALL | (defined('E_STRICT') ? E_STRICT : 0));
ini_set('display_errors', $_errs);
// session
@ -44,7 +44,9 @@ if(get_magic_quotes_gpc()){
}
ini_set('magic_quotes_gpc', 0);
}
set_magic_quotes_runtime(0);
if(get_magic_quotes_runtime()){
set_magic_quotes_runtime(0);
}
$_POST['enc'] = (isset($_POST['enc']) and preg_match('`^[-\w]+$`', $_POST['enc'])) ? $_POST['enc'] : 'utf-8';
@ -132,7 +134,7 @@ function hexdump($d){
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html lang="en" xml:lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=<?php echo htmlspecialchars($_POST['enc']); ?>" />
<meta http-equiv="content-type" content="text/html; charset=utf-8" />
<meta name="description" content="htmLawed <?php echo hl_version();?> test page" />
<style type="text/css"><!--/*--><![CDATA[/*><!--*/
a, a.resizer{text-decoration:none;}
@ -142,15 +144,16 @@ body{background-color:#efefef;}
body, button, div, html, input, p{font-size:13px; font-family:'Lucida grande', Verdana, Arial, Helvetica, sans-serif;}
button, input{font-size: 85%;}
div.help{border-top: 1px dotted gray; margin-top: 15px; padding-top: 15px; color:#999999;}
#inputC, #inputD, #inputF, #inputR, #outputD, #outputF, #outputH, #outputR, #settingF{display:block;}
#inputC, #inputD, #inputF, #inputR, #outputD, #outputF, #outputH, #outputR, #settingF, #diff{display:block;}
#inputC, #settingF{background-color:white; border:1px gray solid; padding:3px;}
#inputC li{margin: 0; padding: 0;}
#inputC ul{margin: 0; padding: 0; margin-left: 14px;}
#inputC input{margin: 0; margin-left: 2px; margin-right: 2px; padding: 1px; vertical-align: middle;}
#inputD{overflow:auto; background-color:#ffff99; border:1px #cc9966 solid; padding:3px;}
#inputR{overflow:auto; background-color:#ffffcc; border:1px #ffcc99 solid; padding:3px;}
#inputC, #settingF, #inputD, #inputR, #outputD, #outputR, textarea{font-size:100%; font-family:'Bitstream vera sans mono', 'courier new', 'courier', monospace;}
#outputD{overflow:auto; background-color: #99ffcc; border:1px #66cc99 solid; padding:3px;}
#inputC, #settingF, #inputD, #inputR, #outputD, #outputR, #diff, textarea{font-size:100%; font-family:'Bitstream vera sans mono', 'courier new', 'courier', monospace;}
#outputD{overflow:auto; background-color: #99ffcc; border:1px #66cc99 solid; padding:3px;}
#diff{overflow:auto; background-color: white; border:1px #dcdcdc solid; padding:3px;}
#outputH{overflow:auto; background-color:white; padding:3px; border:1px #dcdcdc solid;}
#outputR{overflow:auto; background-color: #ccffcc; border:1px #99cc99 solid; padding:3px;}
span.cmtcdata{color: orange;}
@ -259,9 +262,6 @@ function sndUnproc(){
var i = document.getElementById('text');
if(!i){return;}
i = i.value;
i = i.replace(/>/g, '&gt;');
i = i.replace(/</g, '&lt;');
i = i.replace(/"/g, '&quot;');
var w = window.open('htmLawedTest.php?pre=1', 'hlprehtm');
var f = document.createElement('form');
f.enctype = 'application/x-www-form-urlencoded';
@ -269,10 +269,14 @@ function sndUnproc(){
f.acceptCharset = '<?php echo htmlspecialchars($_POST['enc']); ?>';
if(f.style){f.style.display = 'none';}
else{f.visibility = 'hidden';}
f.innerHTML = '<p style="display:none;"><input style="display:none;" type="hidden" name="token" id="token" value="<?php echo $token; ?>" /><input style="display:none;" type="hidden" name="<?php echo htmlspecialchars($_sid); ?>" id="<?php echo htmlspecialchars($_sid); ?>" value="' + readCookie('<?php echo htmlspecialchars($_sid); ?>') + '" /><input style="display:none;" type="hidden" name="inputH" id="inputH" value="'+ i+ '" /></p>';
f.innerHTML = '<p style="display:none;"><input style="display:none;" type="hidden" name="token" id="token" value="<?php echo $token; ?>" /><input style="display:none;" type="hidden" name="<?php echo htmlspecialchars($_sid); ?>" id="<?php echo htmlspecialchars($_sid); ?>" value="' + readCookie('<?php echo htmlspecialchars($_sid); ?>') + '" /></p>';
f.action = 'htmLawedTest.php?pre=1';
f.target = 'hlprehtm';
f.method = 'post';
var t = document.createElement('textarea');
t.name = 'inputH';
t.value = i;
f.appendChild(t);
var b = document.getElementsByTagName('body')[0];
b.appendChild(f);
f.submit();
@ -282,9 +286,6 @@ function sndValidn(id, type){
var i = document.getElementById(id);
if(!i){return;}
i = i.value;
i = i.replace(/>/g, '&gt;');
i = i.replace(/</g, '&lt;');
i = i.replace(/"/g, '&quot;');
var w = window.open('http://validator.w3.org/check', 'validate'+id+type);
var f = document.createElement('form');
f.enctype = 'application/x-www-form-urlencoded';
@ -292,9 +293,13 @@ function sndValidn(id, type){
f.acceptCharset = '<?php echo htmlspecialchars($_POST['enc']); ?>';
if(f.style){f.style.display = 'none';}
else{f.visibility = 'hidden';}
f.innerHTML = '<p style="display:none;"><input style="display:none;" type="hidden" name="fragment" id="fragment" value="'+ i+ '" /><input style="display:none;" type="hidden" name="prefill" id="prefill" value="1" /><input style="display:none;" type="hidden" name="prefill_doctype" id="prefill_doctype" value="'+ type+ '" /><input style="display:none;" type="hidden" name="group" id="group" value="1" /><input type="hidden" name="ss" id="ss" value="1" /></p>';
f.innerHTML = '<p style="display:none;"><input style="display:none;" type="hidden" name="prefill" id="prefill" value="1" /><input style="display:none;" type="hidden" name="prefill_doctype" id="prefill_doctype" value="'+ type+ '" /><input style="display:none;" type="hidden" name="group" id="group" value="1" /><input type="hidden" name="ss" id="ss" value="1" /></p>';
f.action = 'http://validator.w3.org/check';
f.target = 'validate'+id+type;
var t = document.createElement('textarea');
t.name = 'fragment';
t.value = i;
f.appendChild(t);
var b = document.getElementsByTagName('body')[0];
b.appendChild(f);
f.submit();
@ -328,7 +333,7 @@ tRs = {
a.appendChild(document.createTextNode("\u2195"));
a.style.cursor = 'n-resize';
a.className= 'resizer';
a.title = 'click-drag to resize'
a.title = 'click-drag to resize textarea'
tRs.adEv(a, 'mousedown', tRs.initResize);
textareas[i].parentNode.appendChild(a);
}
@ -374,6 +379,58 @@ tRs = {
}
};
tRs.adEv(window, 'load', tRs.adBtn);
// Diff Match and Patch javascript code by Neil Fraser; Apache license 2.0; http://code.google.com/p/google-diff-match-patch/
(function(){function diff_match_patch(){this.Diff_Timeout=1;this.Diff_EditCost=4;this.Match_Threshold=0.5;this.Match_Distance=1E3;this.Patch_DeleteThreshold=0.5;this.Patch_Margin=4;this.Match_MaxBits=32}
diff_match_patch.prototype.diff_main=function(a,b,c,d){"undefined"==typeof d&&(d=0>=this.Diff_Timeout?Number.MAX_VALUE:(new Date).getTime()+1E3*this.Diff_Timeout);if(null==a||null==b)throw Error("Null input. (diff_main)");if(a==b)return a?[[0,a]]:[];"undefined"==typeof c&&(c=!0);var e=c,f=this.diff_commonPrefix(a,b),c=a.substring(0,f),a=a.substring(f),b=b.substring(f),f=this.diff_commonSuffix(a,b),g=a.substring(a.length-f),a=a.substring(0,a.length-f),b=b.substring(0,b.length-f),a=this.diff_compute_(a,
b,e,d);c&&a.unshift([0,c]);g&&a.push([0,g]);this.diff_cleanupMerge(a);return a};
diff_match_patch.prototype.diff_compute_=function(a,b,c,d){if(!a)return[[1,b]];if(!b)return[[-1,a]];var e=a.length>b.length?a:b,f=a.length>b.length?b:a,g=e.indexOf(f);if(-1!=g)return c=[[1,e.substring(0,g)],[0,f],[1,e.substring(g+f.length)]],a.length>b.length&&(c[0][0]=c[2][0]=-1),c;if(1==f.length)return[[-1,a],[1,b]];return(e=this.diff_halfMatch_(a,b))?(f=e[0],a=e[1],g=e[2],b=e[3],e=e[4],f=this.diff_main(f,g,c,d),c=this.diff_main(a,b,c,d),f.concat([[0,e]],c)):c&&100<a.length&&100<b.length?this.diff_lineMode_(a,
b,d):this.diff_bisect_(a,b,d)};
diff_match_patch.prototype.diff_lineMode_=function(a,b,c){var d=this.diff_linesToChars_(a,b),a=d.chars1,b=d.chars2,d=d.lineArray,a=this.diff_main(a,b,!1,c);this.diff_charsToLines_(a,d);this.diff_cleanupSemantic(a);a.push([0,""]);for(var e=d=b=0,f="",g="";b<a.length;){switch(a[b][0]){case 1:e++;g+=a[b][1];break;case -1:d++;f+=a[b][1];break;case 0:if(1<=d&&1<=e){a.splice(b-d-e,d+e);b=b-d-e;d=this.diff_main(f,g,!1,c);for(e=d.length-1;0<=e;e--)a.splice(b,0,d[e]);b+=d.length}d=e=0;g=f=""}b++}a.pop();return a};
diff_match_patch.prototype.diff_bisect_=function(a,b,c){for(var d=a.length,e=b.length,f=Math.ceil((d+e)/2),g=f,h=2*f,j=Array(h),i=Array(h),k=0;k<h;k++)j[k]=-1,i[k]=-1;j[g+1]=0;i[g+1]=0;for(var k=d-e,p=0!=k%2,q=0,s=0,o=0,v=0,u=0;u<f&&!((new Date).getTime()>c);u++){for(var n=-u+q;n<=u-s;n+=2){var l=g+n,m;m=n==-u||n!=u&&j[l-1]<j[l+1]?j[l+1]:j[l-1]+1;for(var r=m-n;m<d&&r<e&&a.charAt(m)==b.charAt(r);)m++,r++;j[l]=m;if(m>d)s+=2;else if(r>e)q+=2;else if(p&&(l=g+k-n,0<=l&&l<h&&-1!=i[l])){var t=d-i[l];if(m>=
t)return this.diff_bisectSplit_(a,b,m,r,c)}}for(n=-u+o;n<=u-v;n+=2){l=g+n;t=n==-u||n!=u&&i[l-1]<i[l+1]?i[l+1]:i[l-1]+1;for(m=t-n;t<d&&m<e&&a.charAt(d-t-1)==b.charAt(e-m-1);)t++,m++;i[l]=t;if(t>d)v+=2;else if(m>e)o+=2;else if(!p&&(l=g+k-n,0<=l&&l<h&&-1!=j[l]&&(m=j[l],r=g+m-l,t=d-t,m>=t)))return this.diff_bisectSplit_(a,b,m,r,c)}}return[[-1,a],[1,b]]};
diff_match_patch.prototype.diff_bisectSplit_=function(a,b,c,d,e){var f=a.substring(0,c),g=b.substring(0,d),a=a.substring(c),b=b.substring(d),f=this.diff_main(f,g,!1,e),e=this.diff_main(a,b,!1,e);return f.concat(e)};
diff_match_patch.prototype.diff_linesToChars_=function(a,b){function c(a){for(var b="",c=0,f=-1,g=d.length;f<a.length-1;){f=a.indexOf("\n",c);-1==f&&(f=a.length-1);var q=a.substring(c,f+1),c=f+1;(e.hasOwnProperty?e.hasOwnProperty(q):void 0!==e[q])?b+=String.fromCharCode(e[q]):(b+=String.fromCharCode(g),e[q]=g,d[g++]=q)}return b}var d=[],e={};d[0]="";var f=c(a),g=c(b);return{chars1:f,chars2:g,lineArray:d}};
diff_match_patch.prototype.diff_charsToLines_=function(a,b){for(var c=0;c<a.length;c++){for(var d=a[c][1],e=[],f=0;f<d.length;f++)e[f]=b[d.charCodeAt(f)];a[c][1]=e.join("")}};diff_match_patch.prototype.diff_commonPrefix=function(a,b){if(!a||!b||a.charAt(0)!=b.charAt(0))return 0;for(var c=0,d=Math.min(a.length,b.length),e=d,f=0;c<e;)a.substring(f,e)==b.substring(f,e)?f=c=e:d=e,e=Math.floor((d-c)/2+c);return e};
diff_match_patch.prototype.diff_commonSuffix=function(a,b){if(!a||!b||a.charAt(a.length-1)!=b.charAt(b.length-1))return 0;for(var c=0,d=Math.min(a.length,b.length),e=d,f=0;c<e;)a.substring(a.length-e,a.length-f)==b.substring(b.length-e,b.length-f)?f=c=e:d=e,e=Math.floor((d-c)/2+c);return e};
diff_match_patch.prototype.diff_commonOverlap_=function(a,b){var c=a.length,d=b.length;if(0==c||0==d)return 0;c>d?a=a.substring(c-d):c<d&&(b=b.substring(0,c));c=Math.min(c,d);if(a==b)return c;for(var d=0,e=1;;){var f=a.substring(c-e),f=b.indexOf(f);if(-1==f)return d;e+=f;if(0==f||a.substring(c-e)==b.substring(0,e))d=e,e++}};
diff_match_patch.prototype.diff_halfMatch_=function(a,b){function c(a,b,c){for(var d=a.substring(c,c+Math.floor(a.length/4)),e=-1,g="",h,j,n,l;-1!=(e=b.indexOf(d,e+1));){var m=f.diff_commonPrefix(a.substring(c),b.substring(e)),r=f.diff_commonSuffix(a.substring(0,c),b.substring(0,e));g.length<r+m&&(g=b.substring(e-r,e)+b.substring(e,e+m),h=a.substring(0,c-r),j=a.substring(c+m),n=b.substring(0,e-r),l=b.substring(e+m))}return 2*g.length>=a.length?[h,j,n,l,g]:null}if(0>=this.Diff_Timeout)return null;
var d=a.length>b.length?a:b,e=a.length>b.length?b:a;if(4>d.length||2*e.length<d.length)return null;var f=this,g=c(d,e,Math.ceil(d.length/4)),d=c(d,e,Math.ceil(d.length/2)),h;if(!g&&!d)return null;h=d?g?g[4].length>d[4].length?g:d:d:g;var j;a.length>b.length?(g=h[0],d=h[1],e=h[2],j=h[3]):(e=h[0],j=h[1],g=h[2],d=h[3]);h=h[4];return[g,d,e,j,h]};
diff_match_patch.prototype.diff_cleanupSemantic=function(a){for(var b=!1,c=[],d=0,e=null,f=0,g=0,h=0,j=0,i=0;f<a.length;)0==a[f][0]?(c[d++]=f,g=j,h=i,i=j=0,e=a[f][1]):(1==a[f][0]?j+=a[f][1].length:i+=a[f][1].length,e&&e.length<=Math.max(g,h)&&e.length<=Math.max(j,i)&&(a.splice(c[d-1],0,[-1,e]),a[c[d-1]+1][0]=1,d--,d--,f=0<d?c[d-1]:-1,i=j=h=g=0,e=null,b=!0)),f++;b&&this.diff_cleanupMerge(a);this.diff_cleanupSemanticLossless(a);for(f=1;f<a.length;){if(-1==a[f-1][0]&&1==a[f][0]){b=a[f-1][1];c=a[f][1];
d=this.diff_commonOverlap_(b,c);e=this.diff_commonOverlap_(c,b);if(d>=e){if(d>=b.length/2||d>=c.length/2)a.splice(f,0,[0,c.substring(0,d)]),a[f-1][1]=b.substring(0,b.length-d),a[f+1][1]=c.substring(d),f++}else if(e>=b.length/2||e>=c.length/2)a.splice(f,0,[0,b.substring(0,e)]),a[f-1][0]=1,a[f-1][1]=c.substring(0,c.length-e),a[f+1][0]=-1,a[f+1][1]=b.substring(e),f++;f++}f++}};
diff_match_patch.prototype.diff_cleanupSemanticLossless=function(a){function b(a,b){if(!a||!b)return 6;var c=a.charAt(a.length-1),d=b.charAt(0),e=c.match(diff_match_patch.nonAlphaNumericRegex_),f=d.match(diff_match_patch.nonAlphaNumericRegex_),g=e&&c.match(diff_match_patch.whitespaceRegex_),h=f&&d.match(diff_match_patch.whitespaceRegex_),c=g&&c.match(diff_match_patch.linebreakRegex_),d=h&&d.match(diff_match_patch.linebreakRegex_),i=c&&a.match(diff_match_patch.blanklineEndRegex_),j=d&&b.match(diff_match_patch.blanklineStartRegex_);
return i||j?5:c||d?4:e&&!g&&h?3:g||h?2:e||f?1:0}for(var c=1;c<a.length-1;){if(0==a[c-1][0]&&0==a[c+1][0]){var d=a[c-1][1],e=a[c][1],f=a[c+1][1],g=this.diff_commonSuffix(d,e);if(g)var h=e.substring(e.length-g),d=d.substring(0,d.length-g),e=h+e.substring(0,e.length-g),f=h+f;for(var g=d,h=e,j=f,i=b(d,e)+b(e,f);e.charAt(0)===f.charAt(0);){var d=d+e.charAt(0),e=e.substring(1)+f.charAt(0),f=f.substring(1),k=b(d,e)+b(e,f);k>=i&&(i=k,g=d,h=e,j=f)}a[c-1][1]!=g&&(g?a[c-1][1]=g:(a.splice(c-1,1),c--),a[c][1]=
h,j?a[c+1][1]=j:(a.splice(c+1,1),c--))}c++}};diff_match_patch.nonAlphaNumericRegex_=/[^a-zA-Z0-9]/;diff_match_patch.whitespaceRegex_=/\s/;diff_match_patch.linebreakRegex_=/[\r\n]/;diff_match_patch.blanklineEndRegex_=/\n\r?\n$/;diff_match_patch.blanklineStartRegex_=/^\r?\n\r?\n/;
diff_match_patch.prototype.diff_cleanupEfficiency=function(a){for(var b=!1,c=[],d=0,e=null,f=0,g=!1,h=!1,j=!1,i=!1;f<a.length;){if(0==a[f][0])a[f][1].length<this.Diff_EditCost&&(j||i)?(c[d++]=f,g=j,h=i,e=a[f][1]):(d=0,e=null),j=i=!1;else if(-1==a[f][0]?i=!0:j=!0,e&&(g&&h&&j&&i||e.length<this.Diff_EditCost/2&&3==g+h+j+i))a.splice(c[d-1],0,[-1,e]),a[c[d-1]+1][0]=1,d--,e=null,g&&h?(j=i=!0,d=0):(d--,f=0<d?c[d-1]:-1,j=i=!1),b=!0;f++}b&&this.diff_cleanupMerge(a)};
diff_match_patch.prototype.diff_cleanupMerge=function(a){a.push([0,""]);for(var b=0,c=0,d=0,e="",f="",g;b<a.length;)switch(a[b][0]){case 1:d++;f+=a[b][1];b++;break;case -1:c++;e+=a[b][1];b++;break;case 0:1<c+d?(0!==c&&0!==d&&(g=this.diff_commonPrefix(f,e),0!==g&&(0<b-c-d&&0==a[b-c-d-1][0]?a[b-c-d-1][1]+=f.substring(0,g):(a.splice(0,0,[0,f.substring(0,g)]),b++),f=f.substring(g),e=e.substring(g)),g=this.diff_commonSuffix(f,e),0!==g&&(a[b][1]=f.substring(f.length-g)+a[b][1],f=f.substring(0,f.length-
g),e=e.substring(0,e.length-g))),0===c?a.splice(b-d,c+d,[1,f]):0===d?a.splice(b-c,c+d,[-1,e]):a.splice(b-c-d,c+d,[-1,e],[1,f]),b=b-c-d+(c?1:0)+(d?1:0)+1):0!==b&&0==a[b-1][0]?(a[b-1][1]+=a[b][1],a.splice(b,1)):b++,c=d=0,f=e=""}""===a[a.length-1][1]&&a.pop();c=!1;for(b=1;b<a.length-1;)0==a[b-1][0]&&0==a[b+1][0]&&(a[b][1].substring(a[b][1].length-a[b-1][1].length)==a[b-1][1]?(a[b][1]=a[b-1][1]+a[b][1].substring(0,a[b][1].length-a[b-1][1].length),a[b+1][1]=a[b-1][1]+a[b+1][1],a.splice(b-1,1),c=!0):a[b][1].substring(0,
a[b+1][1].length)==a[b+1][1]&&(a[b-1][1]+=a[b+1][1],a[b][1]=a[b][1].substring(a[b+1][1].length)+a[b+1][1],a.splice(b+1,1),c=!0)),b++;c&&this.diff_cleanupMerge(a)};diff_match_patch.prototype.diff_xIndex=function(a,b){var c=0,d=0,e=0,f=0,g;for(g=0;g<a.length;g++){1!==a[g][0]&&(c+=a[g][1].length);-1!==a[g][0]&&(d+=a[g][1].length);if(c>b)break;e=c;f=d}return a.length!=g&&-1===a[g][0]?f:f+(b-e)};
diff_match_patch.prototype.diff_prettyHtml=function(a){for(var b=[],c=/&/g,d=/</g,e=/>/g,f=/\n/g,g=0;g<a.length;g++){var h=a[g][0],j=a[g][1],j=j.replace(c,"&amp;").replace(d,"&lt;").replace(e,"&gt;").replace(f,"<span style=\"color: #dcdcdc;\">&not;</span><br>");switch(h){case 1:b[g]='<ins style="background:#ccffcc; text-decoration: none;">'+j+"</ins>";break;case -1:b[g]='<del style="background:#ffffcc; text-decoration: line-through; color: orange;">'+j+"</del>";break;case 0:b[g]="<span>"+j+"</span>"}}return b.join("")};
diff_match_patch.prototype.diff_text1=function(a){for(var b=[],c=0;c<a.length;c++)1!==a[c][0]&&(b[c]=a[c][1]);return b.join("")};diff_match_patch.prototype.diff_text2=function(a){for(var b=[],c=0;c<a.length;c++)-1!==a[c][0]&&(b[c]=a[c][1]);return b.join("")};diff_match_patch.prototype.diff_levenshtein=function(a){for(var b=0,c=0,d=0,e=0;e<a.length;e++){var f=a[e][0],g=a[e][1];switch(f){case 1:c+=g.length;break;case -1:d+=g.length;break;case 0:b+=Math.max(c,d),d=c=0}}return b+=Math.max(c,d)};
diff_match_patch.prototype.diff_toDelta=function(a){for(var b=[],c=0;c<a.length;c++)switch(a[c][0]){case 1:b[c]="+"+encodeURI(a[c][1]);break;case -1:b[c]="-"+a[c][1].length;break;case 0:b[c]="="+a[c][1].length}return b.join("\t").replace(/%20/g," ")};
diff_match_patch.prototype.diff_fromDelta=function(a,b){for(var c=[],d=0,e=0,f=b.split(/\t/g),g=0;g<f.length;g++){var h=f[g].substring(1);switch(f[g].charAt(0)){case "+":try{c[d++]=[1,decodeURI(h)]}catch(j){throw Error("Illegal escape in diff_fromDelta: "+h);}break;case "-":case "=":var i=parseInt(h,10);if(isNaN(i)||0>i)throw Error("Invalid number in diff_fromDelta: "+h);h=a.substring(e,e+=i);"="==f[g].charAt(0)?c[d++]=[0,h]:c[d++]=[-1,h];break;default:if(f[g])throw Error("Invalid diff operation in diff_fromDelta: "+
f[g]);}}if(e!=a.length)throw Error("Delta length ("+e+") does not equal source text length ("+a.length+").");return c};diff_match_patch.prototype.match_main=function(a,b,c){if(null==a||null==b||null==c)throw Error("Null input. (match_main)");c=Math.max(0,Math.min(c,a.length));return a==b?0:a.length?a.substring(c,c+b.length)==b?c:this.match_bitap_(a,b,c):-1};
diff_match_patch.prototype.match_bitap_=function(a,b,c){function d(a,d){var e=a/b.length,g=Math.abs(c-d);return!f.Match_Distance?g?1:e:e+g/f.Match_Distance}if(b.length>this.Match_MaxBits)throw Error("Pattern too long for this browser.");var e=this.match_alphabet_(b),f=this,g=this.Match_Threshold,h=a.indexOf(b,c);-1!=h&&(g=Math.min(d(0,h),g),h=a.lastIndexOf(b,c+b.length),-1!=h&&(g=Math.min(d(0,h),g)));for(var j=1<<b.length-1,h=-1,i,k,p=b.length+a.length,q,s=0;s<b.length;s++){i=0;for(k=p;i<k;)d(s,c+
k)<=g?i=k:p=k,k=Math.floor((p-i)/2+i);p=k;i=Math.max(1,c-k+1);var o=Math.min(c+k,a.length)+b.length;k=Array(o+2);for(k[o+1]=(1<<s)-1;o>=i;o--){var v=e[a.charAt(o-1)];k[o]=0===s?(k[o+1]<<1|1)&v:(k[o+1]<<1|1)&v|(q[o+1]|q[o])<<1|1|q[o+1];if(k[o]&j&&(v=d(s,o-1),v<=g))if(g=v,h=o-1,h>c)i=Math.max(1,2*c-h);else break}if(d(s+1,c)>g)break;q=k}return h};
diff_match_patch.prototype.match_alphabet_=function(a){for(var b={},c=0;c<a.length;c++)b[a.charAt(c)]=0;for(c=0;c<a.length;c++)b[a.charAt(c)]|=1<<a.length-c-1;return b};
diff_match_patch.prototype.patch_addContext_=function(a,b){if(0!=b.length){for(var c=b.substring(a.start2,a.start2+a.length1),d=0;b.indexOf(c)!=b.lastIndexOf(c)&&c.length<this.Match_MaxBits-this.Patch_Margin-this.Patch_Margin;)d+=this.Patch_Margin,c=b.substring(a.start2-d,a.start2+a.length1+d);d+=this.Patch_Margin;(c=b.substring(a.start2-d,a.start2))&&a.diffs.unshift([0,c]);(d=b.substring(a.start2+a.length1,a.start2+a.length1+d))&&a.diffs.push([0,d]);a.start1-=c.length;a.start2-=c.length;a.length1+=
c.length+d.length;a.length2+=c.length+d.length}};
diff_match_patch.prototype.patch_make=function(a,b,c){var d;if("string"==typeof a&&"string"==typeof b&&"undefined"==typeof c)d=a,b=this.diff_main(d,b,!0),2<b.length&&(this.diff_cleanupSemantic(b),this.diff_cleanupEfficiency(b));else if(a&&"object"==typeof a&&"undefined"==typeof b&&"undefined"==typeof c)b=a,d=this.diff_text1(b);else if("string"==typeof a&&b&&"object"==typeof b&&"undefined"==typeof c)d=a;else if("string"==typeof a&&"string"==typeof b&&c&&"object"==typeof c)d=a,b=c;else throw Error("Unknown call format to patch_make.");
if(0===b.length)return[];for(var c=[],a=new diff_match_patch.patch_obj,e=0,f=0,g=0,h=d,j=0;j<b.length;j++){var i=b[j][0],k=b[j][1];if(!e&&0!==i)a.start1=f,a.start2=g;switch(i){case 1:a.diffs[e++]=b[j];a.length2+=k.length;d=d.substring(0,g)+k+d.substring(g);break;case -1:a.length1+=k.length;a.diffs[e++]=b[j];d=d.substring(0,g)+d.substring(g+k.length);break;case 0:k.length<=2*this.Patch_Margin&&e&&b.length!=j+1?(a.diffs[e++]=b[j],a.length1+=k.length,a.length2+=k.length):k.length>=2*this.Patch_Margin&&
e&&(this.patch_addContext_(a,h),c.push(a),a=new diff_match_patch.patch_obj,e=0,h=d,f=g)}1!==i&&(f+=k.length);-1!==i&&(g+=k.length)}e&&(this.patch_addContext_(a,h),c.push(a));return c};diff_match_patch.prototype.patch_deepCopy=function(a){for(var b=[],c=0;c<a.length;c++){var d=a[c],e=new diff_match_patch.patch_obj;e.diffs=[];for(var f=0;f<d.diffs.length;f++)e.diffs[f]=d.diffs[f].slice();e.start1=d.start1;e.start2=d.start2;e.length1=d.length1;e.length2=d.length2;b[c]=e}return b};
diff_match_patch.prototype.patch_apply=function(a,b){if(0==a.length)return[b,[]];var a=this.patch_deepCopy(a),c=this.patch_addPadding(a),b=c+b+c;this.patch_splitMax(a);for(var d=0,e=[],f=0;f<a.length;f++){var g=a[f].start2+d,h=this.diff_text1(a[f].diffs),j,i=-1;if(h.length>this.Match_MaxBits){if(j=this.match_main(b,h.substring(0,this.Match_MaxBits),g),-1!=j&&(i=this.match_main(b,h.substring(h.length-this.Match_MaxBits),g+h.length-this.Match_MaxBits),-1==i||j>=i))j=-1}else j=this.match_main(b,h,g);
if(-1==j)e[f]=!1,d-=a[f].length2-a[f].length1;else if(e[f]=!0,d=j-g,g=-1==i?b.substring(j,j+h.length):b.substring(j,i+this.Match_MaxBits),h==g)b=b.substring(0,j)+this.diff_text2(a[f].diffs)+b.substring(j+h.length);else if(g=this.diff_main(h,g,!1),h.length>this.Match_MaxBits&&this.diff_levenshtein(g)/h.length>this.Patch_DeleteThreshold)e[f]=!1;else{this.diff_cleanupSemanticLossless(g);for(var h=0,k,i=0;i<a[f].diffs.length;i++){var p=a[f].diffs[i];0!==p[0]&&(k=this.diff_xIndex(g,h));1===p[0]?b=b.substring(0,
j+k)+p[1]+b.substring(j+k):-1===p[0]&&(b=b.substring(0,j+k)+b.substring(j+this.diff_xIndex(g,h+p[1].length)));-1!==p[0]&&(h+=p[1].length)}}}b=b.substring(c.length,b.length-c.length);return[b,e]};
diff_match_patch.prototype.patch_addPadding=function(a){for(var b=this.Patch_Margin,c="",d=1;d<=b;d++)c+=String.fromCharCode(d);for(d=0;d<a.length;d++)a[d].start1+=b,a[d].start2+=b;var d=a[0],e=d.diffs;if(0==e.length||0!=e[0][0])e.unshift([0,c]),d.start1-=b,d.start2-=b,d.length1+=b,d.length2+=b;else if(b>e[0][1].length){var f=b-e[0][1].length;e[0][1]=c.substring(e[0][1].length)+e[0][1];d.start1-=f;d.start2-=f;d.length1+=f;d.length2+=f}d=a[a.length-1];e=d.diffs;0==e.length||0!=e[e.length-1][0]?(e.push([0,
c]),d.length1+=b,d.length2+=b):b>e[e.length-1][1].length&&(f=b-e[e.length-1][1].length,e[e.length-1][1]+=c.substring(0,f),d.length1+=f,d.length2+=f);return c};
diff_match_patch.prototype.patch_splitMax=function(a){for(var b=this.Match_MaxBits,c=0;c<a.length;c++)if(!(a[c].length1<=b)){var d=a[c];a.splice(c--,1);for(var e=d.start1,f=d.start2,g="";0!==d.diffs.length;){var h=new diff_match_patch.patch_obj,j=!0;h.start1=e-g.length;h.start2=f-g.length;if(""!==g)h.length1=h.length2=g.length,h.diffs.push([0,g]);for(;0!==d.diffs.length&&h.length1<b-this.Patch_Margin;){var g=d.diffs[0][0],i=d.diffs[0][1];1===g?(h.length2+=i.length,f+=i.length,h.diffs.push(d.diffs.shift()),
j=!1):-1===g&&1==h.diffs.length&&0==h.diffs[0][0]&&i.length>2*b?(h.length1+=i.length,e+=i.length,j=!1,h.diffs.push([g,i]),d.diffs.shift()):(i=i.substring(0,b-h.length1-this.Patch_Margin),h.length1+=i.length,e+=i.length,0===g?(h.length2+=i.length,f+=i.length):j=!1,h.diffs.push([g,i]),i==d.diffs[0][1]?d.diffs.shift():d.diffs[0][1]=d.diffs[0][1].substring(i.length))}g=this.diff_text2(h.diffs);g=g.substring(g.length-this.Patch_Margin);i=this.diff_text1(d.diffs).substring(0,this.Patch_Margin);""!==i&&
(h.length1+=i.length,h.length2+=i.length,0!==h.diffs.length&&0===h.diffs[h.diffs.length-1][0]?h.diffs[h.diffs.length-1][1]+=i:h.diffs.push([0,i]));j||a.splice(++c,0,h)}}};diff_match_patch.prototype.patch_toText=function(a){for(var b=[],c=0;c<a.length;c++)b[c]=a[c];return b.join("")};
diff_match_patch.prototype.patch_fromText=function(a){var b=[];if(!a)return b;for(var a=a.split("\n"),c=0,d=/^@@ -(\d+),?(\d*) \+(\d+),?(\d*) @@$/;c<a.length;){var e=a[c].match(d);if(!e)throw Error("Invalid patch string: "+a[c]);var f=new diff_match_patch.patch_obj;b.push(f);f.start1=parseInt(e[1],10);""===e[2]?(f.start1--,f.length1=1):"0"==e[2]?f.length1=0:(f.start1--,f.length1=parseInt(e[2],10));f.start2=parseInt(e[3],10);""===e[4]?(f.start2--,f.length2=1):"0"==e[4]?f.length2=0:(f.start2--,f.length2=
parseInt(e[4],10));for(c++;c<a.length;){e=a[c].charAt(0);try{var g=decodeURI(a[c].substring(1))}catch(h){throw Error("Illegal escape in patch_fromText: "+g);}if("-"==e)f.diffs.push([-1,g]);else if("+"==e)f.diffs.push([1,g]);else if(" "==e)f.diffs.push([0,g]);else if("@"==e)break;else if(""!==e)throw Error('Invalid patch mode "'+e+'" in: '+g);c++}}return b};diff_match_patch.patch_obj=function(){this.diffs=[];this.start2=this.start1=null;this.length2=this.length1=0};
diff_match_patch.patch_obj.prototype.toString=function(){var a,b;a=0===this.length1?this.start1+",0":1==this.length1?this.start1+1:this.start1+1+","+this.length1;b=0===this.length2?this.start2+",0":1==this.length2?this.start2+1:this.start2+1+","+this.length2;a=["@@ -"+a+" +"+b+" @@\n"];var c;for(b=0;b<this.diffs.length;b++){switch(this.diffs[b][0]){case 1:c="+";break;case -1:c="-";break;case 0:c=" "}a[b+1]=c+encodeURI(this.diffs[b][1])+"\n"}return a.join("").replace(/%20/g," ")};
this.diff_match_patch=diff_match_patch;this.DIFF_DELETE=-1;this.DIFF_INSERT=1;this.DIFF_EQUAL=0;})()
var dmp = new diff_match_patch(); function diffLaunch(){var text1 = document.getElementById('text').value; var text2 = document.getElementById('text2').value; dmp.Diff_Timeout = 0; dmp.Diff_EditCost = 4; var d = dmp.diff_main(text1, text2); var ds = dmp.diff_prettyHtml(d); document.getElementById('diff').innerHTML = ds;
}
//--><!]]></script>
<title>htmLawed (<?php echo hl_version();?>) test</title>
</head>
@ -420,7 +477,7 @@ else{
}
?>
<span style="float:right;" class="help"><span style="font-size: 85%;">Encoding: </span><input type="text" size="8" id="enc" name="enc" style="vertical-align: middle;" value="<?php echo htmlspecialchars($_POST['enc']); ?>" title="IANA-recognized name of the input character-set; can be multiple ;- or space-separated values; may not work in some browsers" /></span>
<span style="float:right;" class="help" title="IANA-recognized name of the input character-set; can be multiple ;- or space-separated values; may not work in some browsers"><span style="font-size: 85%;">Encoding: </span><input type="text" size="8" id="enc" name="enc" style="vertical-align: middle;" value="<?php echo htmlspecialchars($_POST['enc']); ?>" /></span>
</div>
<br style="clear:both;" />
@ -454,6 +511,7 @@ $cfg = array(
'comment'=>array('4', 'nil', 'allow HTML comments', 'nil'),
'css_expression'=>array('2', 'nil', 'allow dynamic expressions in CSS style properties', 'nil'),
'deny_attribute'=>array('1', '0', 'denied attributes', '0', '50', '', 'these'),
'direct_list_nest'=>array('2', 'nil', 'allow direct nesting of a list within another without requiring it to be a list item', 'nil'),
'elements'=>array('', '', 'allowed elements', '50'),
'hexdec_entity'=>array('3', '1', 'convert hexadecimal numeric entities to decimal ones, or vice versa', '0'),
'hook'=>array('', '', 'name of hook function', '25'),
@ -516,23 +574,23 @@ if($do){
}
}
if($cfg['anti_link_spam'] && (!empty($cfg['anti_link_spam11']) or !empty($cfg['anti_link_spam12']))){
if(isset($cfg['anti_link_spam']) && $cfg['anti_link_spam'] && (!empty($cfg['anti_link_spam11']) or !empty($cfg['anti_link_spam12']))){
$cfg['anti_link_spam'] = array($cfg['anti_link_spam11'], $cfg['anti_link_spam12']);
}
unset($cfg['anti_link_spam11'], $cfg['anti_link_spam12']);
if($cfg['anti_mail_spam'] == 1){
if(isset($cfg['anti_mail_spam']) && $cfg['anti_mail_spam'] == 1){
$cfg['anti_mail_spam'] = isset($cfg['anti_mail_spam1'][0]) ? $cfg['anti_mail_spam1'] : 0;
}
unset($cfg['anti_mail_spam11']);
if($cfg['deny_attribute'] == 1){
if(isset($cfg['deny_attribute']) && $cfg['deny_attribute'] == 1){
$cfg['deny_attribute'] = isset($cfg['deny_attribute1'][0]) ? $cfg['deny_attribute1'] : 0;
}
unset($cfg['deny_attribute1']);
if($cfg['tidy'] == 2){
if(isset($cfg['tidy']) && $cfg['tidy'] == 2){
$cfg['tidy'] = isset($cfg['tidy2'][0]) ? $cfg['tidy2'] : 0;
}
unset($cfg['tidy2']);
if($cfg['unique_ids'] == 2){
if(isset($cfg['unique_ids']) && $cfg['unique_ids'] == 2){
$cfg['unique_ids'] = isset($cfg['unique_ids2'][0]) ? $cfg['unique_ids2'] : 1;
}
unset($cfg['unique_ids2']);
@ -540,9 +598,9 @@ if($do){
$cfg['show_setting'] = 'hlcfg';
$st = microtime();
$out = htmLawed($_POST['text'], $cfg, str_replace(array('$', '{'), '', $_POST['spec']));
$out = htmLawed($_POST['text'], $cfg, $_POST['spec']);
$et = microtime();
echo '<br /><a href="htmLawedTest.php" title="[toggle visibility] syntax-highlighted" onclick="javascript:toggle(\'inputR\'); return false;"><span class="notice">Input code &raquo;</span></a> <span class="help" title="tags estimated as half of total &gt; and &lt; chars; values may be inaccurate for non-ASCII text"><small><big>', strlen($_POST['text']), '</big> chars, ~<big>', round((substr_count($_POST['text'], '>') + substr_count($_POST['text'], '<'))/2), '</big> tags</small>&nbsp;</span><div id="inputR" style="display: none;">', format($_POST['text']), '</div><script type="text/javascript">hl(\'inputR\');</script>', (!isset($_POST['text'][$_hlimit]) ? ' <a href="htmLawedTest.php" title="[toggle visibility] hexdump; non-viewable characters like line-returns are shown as dots" onclick="javascript:toggle(\'inputD\'); return false;"><span class="notice">Input binary &raquo;&nbsp;</span></a><div id="inputD" style="display: none;">'. hexdump($_POST['text']). '</div>' : ''), ' <a href="htmLawedTest.php" title="[toggle visibility] finalized internal settings as interpreted by htmLawed; for developers" onclick="javascript:toggle(\'settingF\'); return false;"><span class="notice">Finalized internal settings &raquo;&nbsp;</span></a> <div id="settingF" style="display: none;">', str_replace(array(' ', "\t", ' '), array(' ', '&nbsp; ', '&nbsp; '), nl2br(htmlspecialchars(print_r($GLOBALS['hlcfg']['config'], true)))), '</div><script type="text/javascript">hl(\'settingF\');</script>', '<br /><a href="htmLawedTest.php" title="[toggle visibility] suitable for copy-paste" onclick="javascript:toggle(\'outputF\'); return false;"><span class="notice">Output &raquo;</span></a> <span class="help" title="approx., server-specific value excluding the \'include()\' call"><small>htmLawed processing time <big>', number_format(((substr($et,0,9)) + (substr($et,-10)) - (substr($st,0,9)) - (substr($st,-10))),4), '</big> s</small></span>', (($mem = memory_get_peak_usage()) !== false ? '<span class="help"><small>, peak memory usage <big>'. round(($mem-$pre_mem)/1048576, 2). '</big> <small>MB</small>' : ''), '</small></span><div id="outputF" style="display: block;"><div><textarea id="text2" class="textarea" name="text2" rows="5" cols="100" style="width: 100%;">', htmlspecialchars($out), '</textarea></div><button type="button" onclick="javascript:document.getElementById(\'text2\').focus();document.getElementById(\'text2\').select()" title="select all to copy" style="float:right;">Select all</button>';
echo '<br /><a href="htmLawedTest.php" title="[toggle visibility] syntax-highlighted" onclick="javascript:toggle(\'inputR\'); return false;"><span class="notice">Input code &raquo;</span></a> <span class="help" title="tags estimated as half of total &gt; and &lt; chars; values may be inaccurate for non-ASCII text"><small><big>', strlen($_POST['text']), '</big> chars, ~<big>', ($tag = round((substr_count($_POST['text'], '>') + substr_count($_POST['text'], '<'))/2)), '</big> tag', ($tag > 1 ? 's' : ''), '</small>&nbsp;</span><div id="inputR" style="display: none;">', format($_POST['text']), '</div><script type="text/javascript">hl(\'inputR\');</script>', (!isset($_POST['text'][$_hlimit]) ? ' <a href="htmLawedTest.php" title="[toggle visibility] hexdump; non-viewable characters like line-returns are shown as dots" onclick="javascript:toggle(\'inputD\'); return false;"><span class="notice">Input binary &raquo;&nbsp;</span></a><div id="inputD" style="display: none;">'. hexdump($_POST['text']). '</div>' : ''), ' <a href="htmLawedTest.php" title="[toggle visibility] finalized internal settings as interpreted by htmLawed; for developers" onclick="javascript:toggle(\'settingF\'); return false;"><span class="notice">Finalized internal settings &raquo;&nbsp;</span></a> <div id="settingF" style="display: none;">$config: ', str_replace(array(' ', "\t", ' '), array(' ', '&nbsp; ', '&nbsp; '), nl2br(htmlspecialchars(print_r($GLOBALS['hlcfg']['config'], true)))), '<br />$spec: ', str_replace(array(' ', "\t", ' '), array(' ', '&nbsp; ', '&nbsp; '), nl2br(htmlspecialchars(print_r($GLOBALS['hlcfg']['spec'], true)))), '</div><script type="text/javascript">hl(\'settingF\');</script>', '<br /><a href="htmLawedTest.php" title="[toggle visibility] suitable for copy-paste" onclick="javascript:toggle(\'outputF\'); return false;"><span class="notice">Output &raquo;</span></a> <span class="help" title="approx., server-specific value excluding the \'include()\' call"><small>htmLawed processing time <big>', number_format(((substr($et,0,9)) + (substr($et,-10)) - (substr($st,0,9)) - (substr($st,-10))),4), '</big> s</small></span>', (($mem = memory_get_peak_usage()) !== false ? '<span class="help"><small>, peak memory usage <big>'. round(($mem-$pre_mem)/1048576, 2). '</big> <small>MB</small>' : ''), '</small></span><div id="outputF" style="display: block;"><div><textarea id="text2" class="textarea" name="text2" rows="5" cols="100" style="width: 100%;">', htmlspecialchars($out), '</textarea></div><button type="button" onclick="javascript:document.getElementById(\'text2\').focus();document.getElementById(\'text2\').select()" title="select all to copy" style="float:right;">Select all</button>';
if($_w3c_validate && $validation)
{
?>
@ -552,7 +610,7 @@ if($do){
<?php
}
echo '</div><br /><a href="htmLawedTest.php" title="[toggle visibility] syntax-highlighted" onclick="javascript:toggle(\'outputR\'); return false;"><span class="notice">Output code &raquo;</span></a><div id="outputR" style="display: block;">', format($out), '</div><script type="text/javascript">hl(\'outputR\');</script>', (!isset($_POST['text'][$_hlimit]) ? '<br /><a href="htmLawedTest.php" title="[toggle visibility] hexdump; non-viewable characters like line-returns are shown as dots" onclick="javascript:toggle(\'outputD\'); return false;"><span class="notice">Output binary &raquo;</span></a><div id="outputD" style="display: none;">'. hexdump($out). '</div>' : ''), '<br /><a href="htmLawedTest.php" title="[toggle visibility] XHTML 1 Transitional doctype" onclick="javascript:toggle(\'outputH\'); return false;"><span class="notice">Output rendered &raquo;</span></a><div id="outputH" style="display: block;">', $out, '</div>';
echo '</div><br /><a href="htmLawedTest.php" title="[toggle visibility] syntax-highlighted" onclick="javascript:toggle(\'outputR\'); return false;"><span class="notice">Output code &raquo;</span></a><div id="outputR" style="display: block;">', format($out), '</div><script type="text/javascript">hl(\'outputR\');</script>', (!isset($_POST['text'][$_hlimit]) ? ' <a href="htmLawedTest.php" title="[toggle visibility] hexdump; non-viewable characters like line-returns are shown as dots" onclick="javascript:toggle(\'outputD\'); return false;"><span class="notice">Output binary &raquo;</span></a><div id="outputD" style="display: none;">'. hexdump($out). '</div>' : ''), ' <a href="htmLawedTest.php" title="[toggle visibility] inline output-input diff; might not be perfectly accurate, semantically or otherwise " onclick="javascript:toggle(\'diff\'); diffLaunch(); return false;"><span class="notice">Diff &raquo;</span></a> <div id="diff" style="display: none;"></div><br /><a href="htmLawedTest.php" title="[toggle visibility] XHTML 1 Transitional doctype" onclick="javascript:toggle(\'outputH\'); return false;"><span class="notice">Output rendered &raquo;</span></a><div id="outputH" style="display: block;">', $out, '</div>';
}
else{
?>

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1,8 +1,8 @@
/*
htmLawed_TESTCASE.txt, 23 April 2009
htmLawed 1.1.8.1, 16 July 2009
htmLawed_TESTCASE.txt, 27 August 2013
htmLawed 1.1.16, 29 August 2013
Copyright Santosh Patnaik
GPL v3 license
Dual licensed with LGPL 3 and GPL 2+
A PHP Labware internal utility - http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed
*/
@ -27,6 +27,8 @@ character encoding to Unicode/UTF-8
<strong>Duplicated:</strong> <a id="id5" id="id6">a</a><br />
<strong>Deprecated:</strong> <a id="id7" target="self" name="n">a</a>, <hr noshade="noshade" /><br />
<strong>Casing:</strong> <a HREF=""></a><br />
<strong>Custom:</strong> <img alt="image" my:data="portrait" /><br />
<strong>Data-*:</strong> <a data-xml="x" data-xmnt="x" data-xmlnt="x" data-xmn:t="x" data-xmxm="x">a</a><br />
<strong>Admin-restricted?:</strong> <a href="x" onclick="alert();"></a>
<h6>Attribute values</h6>
@ -46,6 +48,11 @@ character encoding to Unicode/UTF-8
<blockquote><div>abc</div>def</blockquote><br />
<blockquote>abc<div>def</div>ghi</blockquote><br />
abc<div>def</div>ghi<br />
<blockquote>QQQ<div>x</div><!-- comment --></blockquote><br />
<blockquote><div>x</div><!-- comment -->QQQ</blockquote><br />
<blockquote><!-- comment --><div>x</div>QQQ<div>x</div></blockquote><br />
<blockquote><div>x<!-- comment --></div>QQQ</blockquote><p>x</p><br />
<br />
(try with blockquote parent)
<h6>CDATA sections</h6>
@ -94,6 +101,15 @@ The PHP <s>software</s> script used for this <strike>web-page</strike> webpage i
<area href="5" shape="Rect" coords="0,0,118,28">
</map></object>
<param name="name">value</param>
<object id="obj1">
<param name="param1">
<object id="obj2">
<param name="param2">
</object>
</object>
<h6>Complex-4: nested and other tables</h6>
<table border="1" bgcolor="red"> <tr> <td> Cell </td> <td colspan="2" rowspan="2"> <table border="1" bgcolor="green"> <tr> <td> Cell </td> <td colspan="2" rowspan="2"> </td> </tr> <tr> <td> Cell </td> </tr> <tr> <td> Cell </td> <td> Cell </td> <td> Cell </td> </tr> </table> </td> </tr> <tr> <td> Cell </td> </tr> <tr> <td> Cell </td> <td> Cell </td> <td> Cell </td> </tr> </table><br />
@ -119,8 +135,9 @@ Disallowed tag p
<strong>Invalid:</strong> <image src="s" alt="a" /><br />
<strong>Empty:</strong> <img src="s" alt="a" />, <img src="s" alt="a"></img>, <img src="s" alt="a">text</img><br />
<strong>Content invalid:</strong> <a href="h">1<a>2</a></a><br />
<strong>Content invalid?:</strong> <form></form><br /> (try setting 'form' as parent)
<strong>Casing:</strong> <A href=""></a>
<strong>Content invalid?:</strong> <form></form><br /> (try setting 'form' as parent)<br />
<strong>Casing:</strong> <A href=""></a><br />
<strong>Check for tidy:</strong> <br /><hr /></div><hr /></div><hr /></div><div>hi</div>
<h6>Entities</h6>
@ -181,10 +198,20 @@ text <img src="none" alt="none" /> <b>t<em> e <strong> x </strong> t</em></b>
<h6>HTML comments (also CDATA)</h6>
Special characters inside: <!-- <![CDATA check ]]> -->, <!-- 3 < 4 > 3.5, & 4 &gt; 4 -->, <!-- che--ck -->, <!--[if !IE]> <--><a>c</a><!--> <![endif]--><br />
Normal: <!-- check -->, <!--check -->, <em>comment:<!-- check --></em><!-- check -->, <table><!-- check --><tr><td>text not allowed</td></tr></table><br />
Malformed: <![cdata check ]]>, < ![CDATA check ]]>, < ![CDATA check ] ]><br />
Invalid: <em <!-- check -->>comment in tag content</em>, <!--check-->
<strong>Script inside:</strong> <!--[if gte IE 4]>
<SCRIPT>alert('XSS');</SCRIPT>
<![endif]--><br />
<strong>Special characters inside: <!-- <![CDATA check ]]> -->, <!-- 3 < 4 > 3.5, & 4 &gt; 4 -->, <!-- che--ck -->, <!--[if !IE]> <--><a>c</a><!--> <![endif]--><br />
<strong>Normal:</strong> <!-- check -->, <!--check -->, <em>comment:<!-- check --></em><!-- check -->, <table><!-- check --><tr><td>text not allowed</td></tr></table><br />
<strong>Malformed:</strong> <![cdata check ]]>, < ![CDATA check ]]>, < ![CDATA check ] ]><br />
Invalid:</strong> <em <!-- check -->>comment in tag content</em>, <!--check-->
<h6>HTML5</h6>
<strong>figure and figcaption:</strong> <figure><img src="picture.jpg" alt="picture"><figcaption>Caption for the awesome picture</figcaption></figure>
<strong>article:</strong> <h1>A</h1><p>B</p><article><h2>C</h2></article><article><h2>E</h2><p>F</p><p>G</p></article>
<strong>meter</strong>: <p>Heat <meter min="100" max="200" value="150">150</meter>.</p>
<strong>datalist</strong>: <input list="b" /><datalist id="b"><option value="c"><option value="d"></datalist>
<h6>Ins-Del</h6>
@ -224,6 +251,11 @@ Invalid: <em <!-- check -->>comment in tag content</em>, <!--check-->
<li>l3</li>
<li>l4<ol><li>lo3</li><li>lo4<ol><li>lo5</li></ol></li></ol></li>
</ul><br />
<strong>Nested, directly</strong>: <ul>
<li>l1</li>
<ol>l2</ol>
<li>l3</li>
</ul><br />
<strong>Nested, close-tags omitted</strong>: <ul>
<li>l1</li>
<li>l2<ol><li>lo1<li>lo2</ol>
@ -241,12 +273,34 @@ Invalid: <em <!-- check -->>comment in tag content</em>, <!--check-->
</form>
</li></ul>
</td></tr></table></li></ol>
<strong>Menu</strong>: <menu type="toolbar"><li><menu label="File">
<button type="button" onclick="new()">New...</button>
</menu></li><li><menu label="Edit"><button type="button" onclick="cut()">Cut...</button></menu></li>
</menu>
<h6>Microdata</h6>
<div itemscope itemtype="http://data-vocabulary.org/Person">
I am <span itemprop="name">X</span> but people call me <span itemprop="nickname">Y</span>.
Find me at <a href="http://www.xy.com" itemprop="url">www.xy.com</a>
</div>
<h6>Microsoft Word</h6>
<strong>Proprietary tag</strong>: <p class=3DMsoNormal><o:p>&nbsp;</o:p></p><br />
<strong>XML declaration</strong>: <?xml:namespace prefix = o ns = "urn:schemas-microsoft-com:office:office" /><br />
<strong>XML-invalid character code-point (may not replicate)</strong>: <p class=3DMsoNormal>“Where is he?” asked both Mary the one so lovely and Jane.</p>
<h6>Nesting</h6>
<strong>Block or inline a</strong>: <p><a href="link">text</a></p><a href="link"><div>hi</div></a><br />
<h6>Non-English text-1</h6>
Inscrieţi-vă acum la a Zecea Conferinţă Internaţională<br />
გთხოვთ ახლავე გაიაროთ რეგისტრაცია<br />
večjezično računalništvo<br />
<a title="อ.อ่าง">อ.อ่าง</a><br />
<a title="הירשמו
כעת לכנס ">Зарегистрируйтесь сейчас
на Десятую Международную Конференцию по</a><br />
@ -288,6 +342,7 @@ na Alemanha.
<rp>(</rp><rt>aaa</rt><rp>)</rp>
</ruby>
<h6>Tables</h6>
<strong>Omitted closing tags:</strong> <table>
@ -314,12 +369,21 @@ na Alemanha.
<tr><td>r2c1<td>r2c2
</table><br />
<h6>Tag transformation</h6>
<strong>Font element intended as 'inline' element:</strong> <p><font color='red'>hi</font></p><br />
<strong>Font element intended as 'block' element:</strong> <div><font color='red'><div>hi</div></font></div><br />
<strong>Font element intended as 'block' element:</strong> <center><font color='red'><div>hi</div><div>QQQ</div></font></center><br />
<h6>Tidy</h6>
<strong>White-space handling:</strong> abc<em> def </em> ghi abc <em>def</em> ghi
<h6>URLs</h6>
<strong>Relative and absolute:</strong> <a href="mailto:x"></a>, <a href="http://a.com/b/c/d.f"></a>, <a href="./../d.f"></a>, <a href="./d.f"></a>, <a href="d.f"></a>, <a href="#s"></a>, <a href="./../../d.f#s"></a><br />
(try base URL value of 'http://a.com/b/')<br />
<strong>CSS URLs:</strong> <div style="background-image: url('a.gif');"></div>, <div style="background-image: URL(&quot;a.gif&quot;);"></div>, <div style="background-image: url('http://a.com/a.gif');"></div>, <div style="background-image: url('./../a.gif');"></div>, <div style="background-image: &#117;r&#x6C;('js&#58;xss'&#x29;"></div><br />
<strong>Anti-spam:</strong> (try regex for 'http://a.com', etc.) <a href="mailto:x@y.com"></a>, <a href="http://a.com/b@d.f"></a>, <a href="a.com/d.f" rel="nofollow"></a>, <a href="a.com/d.f" rel="1, 2"></a>, <a href="a.com/d.f"></a>, <a href="b.com/d.f"></a>, <a href="c.com/d.f"></a><br />
<strong>Double URLs:</strong> <a style="behaviour: url(foo) url(http://example.com/xss.htc)">b</a><br />
<strong>Anti-spam:</strong> (try regex for 'http://a.com', etc.) <a href="mailto:x@y.com"></a>, <a href="http://a.com/b@d.f"></a>, <a href="a.com/d.f" rel="nofollow"></a>, <a href="a.com/d.f" rel="1, 2"></a>, <a href="a.com/d.f"></a>, <a href="b.com/d.f"></a>, <a href="c.com/d.f">, <a href="denied:http://c.com/d.f"></a><br />
<h6>XSS</h6>
@ -338,6 +402,7 @@ src=&#106;&#97;&#118;&#97;&#115;&#99;&#114;&#105;&#112;&#116;&#58;&#97;&#108;&#1
<a style=";-moz-binding:url(http://lukasz.pilorz.net/xss/xss.xml#xss)" href="http://example.com">test</a><br />
<strong>Bad IE7:</strong> <a href="http://x&x=%22+style%3d%22background-image%3a+expression%28alert
%28%27xss%3f%29%29">x</a><br />
<strong>Opera:</strong> <a href="\xE2\x80\x83javascript:alert(123)">link</a>
<strong>Bad IE7:</strong> <a style=color:expr/*comment*/ession(alert(document.domain))>xxx</a><br />
<strong>Bad IE7:</strong> <a href="xxx" style="background: exp&#x72;ession(alert('xss'));">xxx</a><br />
<strong>Bad IE7:</strong> <a href="xxx" style="background: &#101;xpression(alert('xss'));">xxx</a><br />
@ -367,4 +432,19 @@ script:eval(document.all.mycode.expr)')">hi</a><br />
3 < 4 <br />
3 > 4 <br />
> 3 <br />
> 3 <br />
<._.> hi! <br />
<<< ALERT >>> <br />
<![if !vml]> some stuff <![endif]> <br />
<?xml:namespace prefix = o ns = "urn:schemas-microsoft-com:office:office" /> <br />
<uml:ns ns = "urn:www"> <br />
<uml:ns ns = 'urn:www'> <br />
if(13<age AND 21>age){say 'teen'} <br />
age >51 and a smoking history of >51 pack-years <b>was</b> <br />
age > 51 and a smoking history of >51 pack-years <b>was</b> <br />
age <51 and a smoking history of <51 pack-years <b>was</b> <br />
age < 51 and a smoking history of < 51 pack-years <b>was</b> <br />
<b>age >51 and a smoking history of >51 pack-years</b> <br />
<b>age > 51 and a smoking history of >51 pack-years</b> <br />
<b>age <51 and a smoking history of <51 pack-years</b> <br />
<b>age < 51 and a smoking history of < 51 pack-years</b> <br />