demo.php

   1 <?php
   2
   3 // major TODO: hook into some sort of templating system that utilizes
   4 // XHTML Compiler to process the template (cacheable, of course), before
   5 // passing it along to this script
   6
   7 // using _REQUEST because we accept GET and POST requests
   8
   9 function getFormMethod() {
  10     return (isset($_REQUEST['post'])) ? 'post' : 'get';
  11 }
  12 function escapeHTML($html) {
  13     return htmlspecialchars(
  14         HTMLPurifier_Encoder::cleanUTF8($html), ENT_COMPAT, 'UTF-8');
  15 }
  16 function isLocal() {
  17     static $name = false;
  18     if (!$name) {
  19         if (file_exists($dir = 'xhtml-compiler/conf/name.txt')) {
  20             $name = trim(file_get_contents($dir));
  21         } elseif (file_exists('xhtml-compiler/local.txt')) {
  22             $name = 'EZYANG';
  23         } elseif (file_exists('local.txt')) {
  24             $name = 'EZYANG';
  25         }
  26     }
  27     return $name == 'EZYANG' || $name == 'EZYANG2';
  28 }
  29
  30 if (empty($_REQUEST['experimental'])) {
  31     require_once 'live/library/HTMLPurifier.auto.php';
  32 } elseif (!isLocal()) {
  33     require_once 'dev/library/HTMLPurifier.auto.php';
  34 } else {
  35     require_once '../htmlpurifier/library/HTMLPurifier.auto.php';
  36 }
  37 require_once 'HTMLPurifier/Printer/ConfigForm.php';
  38
  39 // Permissible configuration options have to be chosen carefully; HTML
  40 // Purifier wasn't designed for unfriendly user configuration, so
  41 // certain configuration directives can be used to cause XSS attacks
  42 // because they're not validated at all.
  43
  44 $allowed_lite = array(
  45     'Core.CollectErrors',
  46     'URI.DisableExternalResources',
  47     'URI.Munge',
  48     'HTML.TidyLevel',
  49     'HTML.Doctype',
  50     'HTML.Allowed',
  51     'HTML.SafeObject',
  52     'HTML.FlashCompat',
  53     'CSS.AllowedProperties',
  54     'AutoFormat',
  55     '-AutoFormat.Custom',
  56     '-AutoFormat.PurifierLinkify',
  57     '-AutoFormat.PurifierLinkify.DocURL',
  58     '-AutoFormat.RemoveEmpty.RemoveNbsp',
  59     '-AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions'
  60 );
  61
  62 $config = HTMLPurifier_Config::loadArrayFromForm($_REQUEST, 'filter', $allowed_lite);
  63 $purifier = new HTMLPurifier($config);
  64
  65 if (!empty($_REQUEST['strict'])) {
  66     // backwards-compatibility
  67     // (muting deprecated error)
  68     @$config->set('HTML', 'Strict', true);
  69 }
  70 if (!empty($_REQUEST['experimental'])) {
  71     //require_once 'HTMLPurifier/Lexer/PH5P.php';
  72     //$config->set('Core', 'LexerImpl', 'PH5P');
  73     //$config->set('HTML.SafeObject', true);
  74     //$config->set('HTML.FlashCompat', true);
  75 }
  76
  77 if (file_exists('demo.custom.php') && isLocal()) include 'demo.custom.php';
  78
  79 $definition = $config->getHTMLDefinition();
  80 $doctype = $definition->doctype;
  81
  82 if ($doctype->xml && stripos($_SERVER["HTTP_ACCEPT"], 'application/xhtml+xml') !== false && !isset($_REQUEST['debug'])) {
  83     $type = 'application/xhtml+xml';
  84 } else {
  85     $type = 'text/html';
  86 }
  87 header("Content-type:$type;charset=UTF-8");
  88
  89 // prevent PHP versions with shorttags from barfing
  90 if ($doctype->xml) {
  91     echo '<?xml version="1.0" encoding="UTF-8" ?>' . PHP_EOL;
  92 }
  93
  94 if (!empty($doctype->dtdPublic) && !empty($doctype->dtdSystem)) {
  95     echo '<!DOCTYPE html PUBLIC "'.$doctype->dtdPublic.'" "'.$doctype->dtdSystem.'">' . PHP_EOL;
  96 }
  97
  98 if ($doctype->xml) {
  99     echo '<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">' . PHP_EOL;
 100     $END = ' /';
 101 } else {
 102     echo '<html lang="en">' . PHP_EOL;
 103     $END = '';
 104 }
 105
 106 ?><head>
 107     <title>HTML Purifier Live Demo</title>
 108     <!-- make sure all empty elements that are not generated are
 109      appropriately ended -->
 110     <meta name="author" content="Edward Z. Yang"<?php echo $END; ?>>
 111     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"<?php echo $END; ?>>
 112     <link rel="icon" href="favicon.ico" type="image/x-icon"<?php echo $END; ?>>
 113     <link rel="shortcut icon" href="favicon.ico" type="image/x-icon"<?php echo $END; ?>>
 114     <link rel="stylesheet" href="common.css" type="text/css"<?php echo $END; ?>>
 115     <link rel="stylesheet" href="demo.css" type="text/css"<?php echo $END; ?>>
 116     <link rel="stylesheet" href="live/library/HTMLPurifier/Printer/ConfigForm.css" type="text/css"<?php echo $END; ?>>
 117     <script defer="defer" type="text/javascript" src="live/library/HTMLPurifier/Printer/ConfigForm.js"></script>
 118 </head>
 119 <body>
 120 <div id="logo"></div>
 121 <div id="header"><a href=".">HTML Purifier</a></div>
 122 <?php
 123 if (file_exists('navigation.frag')) {
 124     readfile('navigation.frag');
 125 } else { ?>
 126     <div><strong>Please navigate to <a href="navigation.html">navigation.html</a> to regenerate menu</strong></div>
 127 <?php }
 128 ?>
 129 <div id="main">
 130 <h1 id="title">Live Demo</h1>
 131 <div id="content">
 132 <?php
 133
 134 if (!empty($_REQUEST['html'])) { // start result
 135
 136     if (strlen($_REQUEST['html']) > 50000) {
 137         ?>
 138         <p>Request exceeds maximum allowed text size of 50kb.</p>
 139         <?php
 140     } else { // start main processing
 141
 142     $html = get_magic_quotes_gpc() ? stripslashes($_REQUEST['html']) : $_REQUEST['html'];
 143     $pure_html = $purifier->purify($html);
 144
 145 ?>
 146 <p>Here is your purified HTML:</p>
 147 <div id="output">
 148 <?php if(getFormMethod() == 'get') {
 149 // calculate image
 150 $img = false;
 151 if ($doctype->name == 'HTML 4.01 Transitional' || $doctype->name == 'HTML 4.01 Strict') {
 152     $img = 'http://www.w3.org/Icons/valid-html401';
 153 } elseif ($doctype->name == 'XHTML 1.0 Transitional' || $doctype->name == 'XHTML 1.0 Strict') {
 154     $img = 'http://www.w3.org/Icons/valid-xhtml10';
 155 } elseif ($doctype->name == 'XHTML 1.1') {
 156     $img = 'http://www.w3.org/Icons/valid-xhtml11';
 157 }
 158 ?>
 159   <div id="w3c-validator">
 160     <a href="http://validator.w3.org/check?uri=referer" title="Valid <?php echo escapeHTML($doctype->name); ?>">
 161     <?php if ($img) { ?>
 162       <img
 163         src="<?php echo escapeHTML($img); ?>" height="31" width="88"
 164         alt="Valid <?php echo escapeHTML($doctype->name); ?>"<?php echo $END; ?>>
 165     <?php } else { ?>
 166       Valid <?php echo escapeHTML($doctype->name); ?>
 167     <?php } ?>
 168     </a>
 169   </div>
 170 <?php } ?>
 171 <?php
 172
 173 echo $pure_html;
 174
 175 ?>
 176 <div class="clear"></div>
 177 </div>
 178 <?php if (@$config->get('Core', 'CollectErrors')) {
 179     $e = $purifier->context->get('ErrorCollector');
 180     $class = $e->getRaw() ? 'fail' : 'pass';
 181 ?>
 182     <p>Here are errors that occurred during purification:</p>
 183     <div id="errors" class="<?php echo $class ?>">
 184     <?php
 185     echo $e->getHTMLFormatted($config);
 186     ?>
 187 </div>
 188 <?php } ?>
 189 <p>Here is the source code of the purified HTML:</p>
 190 <pre id="source"><?php echo escapeHTML($pure_html); ?></pre>
 191 <?php
 192 if (getFormMethod() == 'post') { // start POST validation notice
 193 ?>
 194     <p>If you would like to validate the code with
 195     <a href="http://validator.w3.org/#validate-by-input">W3C's
 196     validator</a>, copy and paste the <em>entire</em> demo page's source.</p>
 197 <?php
 198 } // end POST validation notice
 199
 200 ?>
 201 <p>Share this purification using the <a href="javascript:var%20e=document.createElement('script');e.setAttribute('language','javascript');e.setAttribute('src','http://bit.ly/bookmarklet/load.js');document.body.appendChild(e);void(0);">bit.ly URL shortener</a>.</p>
 202 <?php
 203
 204 } // end main processing
 205
 206 // end result
 207 } else {
 208
 209 ?>
 210 <p>Welcome to the live demo.  Enter some HTML and see how HTML Purifier
 211 will filter it.</p>
 212 <?php
 213
 214 }
 215
 216 ?>
 217 <form id="filter" action="demo.php<?php
 218 echo '?' . getFormMethod();
 219 if (isset($_REQUEST['profile']) || isset($_REQUEST['XDEBUG_PROFILE'])) {
 220     echo '&amp;XDEBUG_PROFILE=1';
 221 } ?>" method="<?php echo getFormMethod();  ?>">
 222     <fieldset>
 223         <legend>HTML Purifier Input (<?php echo getFormMethod(); ?>)</legend>
 224
 225         <?php
 226 $form_printer = new HTMLPurifier_Printer_ConfigForm('filter', 'http://htmlpurifier.org/live/configdoc/plain.html#%s', 14);
 227 echo $form_printer->render($config, $allowed_lite, false);
 228         ?>
 229
 230         <div id="textarea">
 231         <textarea name="html" cols="60" rows="15"><?php
 232 if (isset($html)) echo escapeHTML($html);
 233         ?></textarea>
 234         </div>
 235
 236         <p class="lead">
 237             By default, HTML Purifier may remove some of your spacing or
 238             indentation. Turn on CollectErrors or experimental features in
 239             order to fully preserve whitespace.
 240         </p>
 241         <?php if (getFormMethod() == 'get') { ?>
 242             <p><strong>Warning:</strong> GET request method can only hold
 243                 8129 characters (probably less depending on your browser).
 244                 If you need to test anything
 245                 larger than that, try the <a href="?post">POST form</a>.</p>
 246         <?php } ?>
 247         <div id="controls">
 248             <input type="submit" value="Submit" name="submit" class="button"<?php echo $END; ?>>
 249             Use <abbr class="elaborates" title="This runs code from the master Git repository branch.">experimental features</abbr>: <input type="checkbox" value="1" <?php if(!empty($_REQUEST['experimental'])) {echo 'checked="checked" ';} ?>name="experimental"<?php echo $END; ?>>
 250         </div>
 251     </fieldset>
 252 </form>
 253 <p class="lead">Try the form in <a href="?get">GET</a> and <a href="?post">POST</a> request
 254 flavors (GET is easy to validate with W3C, but POST allows larger inputs).
 255 Don't know what to test? Try out these sample filterings:</p>
 256 <ul>
 257     <li><a href="demo.php?html=%3Cimg+src%3D%22javascript%3Aevil%28%29%3B%22+onload%3D%22evil%28%29%3B%22+%2F%3E">Malicious code removed</a></li>
 258     <li><a href="demo.php?html=%3Cb%3EBold&amp;submit=Submit">Missing end tags fixed</a></li>
 259     <li><a href="demo.php?html=%3Cb%3EInline+%3Cdel%3Econtext+%3Cdiv%3ENo+block+allowed%3C%2Fdiv%3E%3C%2Fdel%3E%3C%2Fb%3E&amp;submit=Submit">Illegal nesting fixed</a></li>
 260     <li><a href="demo.php?html=%3Ccenter%3ECentered%3C%2Fcenter%3E&amp;filter%5BHTML.Doctype%5D=XHTML+1.0+Strict&amp;submit=Submit">Deprecated tags converted</a></li>
 261     <li><a href="demo.php?html=%3Cspan+style%3D%22color%3A%23COW%3Bfloat%3Aaround%3Btext-decoration%3Ablink%3B%22%3EText%3C%2Fspan%3E&amp;submit=Submit"><abbr>CSS</abbr> validated</a></li>
 262     <li><a href="demo.php?html=%3Ctable%3E%0D%0A++%3Ccaption%3E%0D%0A++++Cool+table%0D%0A++%3C%2Fcaption%3E%0D%0A++%3Ctfoot%3E%0D%0A++++%3Ctr%3E%0D%0A++++++%3Cth%3EI+can+do+so+much%21%3C%2Fth%3E%0D%0A++++%3C%2Ftr%3E%0D%0A++%3C%2Ftfoot%3E%0D%0A++%3Ctr%3E%0D%0A++++%3Ctd+style%3D%22font-size%3A16pt%3B%0D%0A++++++color%3A%23F00%3Bfont-family%3Asans-serif%3B%0D%0A++++++text-align%3Acenter%3B%22%3EWow%3C%2Ftd%3E%0D%0A++%3C%2Ftr%3E%0D%0A%3C%2Ftable%3E&amp;experimental=1&amp;submit=Submit">Rich formatting preserved</a></li>
 263 </ul>
 264 </div>
 265 </div>
 266 </body>
 267 </html>