Add AutoFormat.RemoveEmpty.Predicate, fixes #35.

Signed-off-by: Edward Z. Yang <ezyang@cs.stanford.edu>

NEWS

@@ -12,6 +12,11 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 4.7.0, unknown release date
 # opacity is now considered a "tricky" CSS property rather than a
   proprietary one.
+! %AutoFormat.RemoveEmpty.Predicate for specifying exactly when
+  an element should be considered "empty" (maybe preserve if it
+  has attributes), and modify iframe support so that the iframe
+  is removed if it is missing a src attribute.  Thanks meeva for
+  reporting.
 - Don't truncate upon encountering </div> when using DOMLex.  Thanks
   Myrto Christina for finally convincing me to fix this.
 - Update YouTube filter for new code.

configdoc/usage.xml

@@ -481,6 +481,11 @@
    <line>47</line>
   </file>
  </directive>
+ <directive id="AutoFormat.RemoveEmpty.Predicate">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>48</line>
+  </file>
+ </directive>
  <directive id="Core.AggressivelyFixLt">
   <file name="HTMLPurifier/Lexer/DOMLex.php">
    <line>54</line>

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt

@@ -0,0 +1,14 @@
+AutoFormat.RemoveEmpty.Predicate
+TYPE: hash
+VERSION: 4.7.0
+DEFAULT: array('colgroup' => array(), 'th' => array(), 'td' => array(), 'iframe' => array('src'))
+--DESCRIPTION--
+<p>
+  Given that an element has no contents, it will be removed by default, unless
+  this predicate dictates otherwise.  The predicate can either be an associative
+  map from tag name to list of attributes that must be present for the element
+  to be considered preserved: thus, the default always preserves <code>colgroup</code>,
+  <code>th</code> and <code>td</code>, and also <code>iframe</code> if it
+  has a <code>src</code>.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/Injector/RemoveEmpty.php

@@ -28,10 +28,10 @@ class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
     private $removeNbspExceptions;
 
     /**
+     * Cached contents of %AutoFormat.RemoveEmpty.Predicate
      * @type array
-     * TODO: make me configurable
      */
-    private $_exclude = array('colgroup' => 1, 'th' => 1, 'td' => 1, 'iframe' => 1);
+    private $exclude;
 
     /**
      * @param HTMLPurifier_Config $config
@@ -45,6 +45,7 @@ class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
         $this->context = $context;
         $this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp');
         $this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions');
+        $this->exclude = $config->get('AutoFormat.RemoveEmpty.Predicate');
         $this->attrValidator = new HTMLPurifier_AttrValidator();
     }
 
@@ -75,11 +76,15 @@ class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
             break;
         }
         if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) {
-            if (isset($this->_exclude[$token->name])) {
-                return;
-            }
             $this->attrValidator->validateToken($token, $this->config, $this->context);
             $token->armor['ValidateAttributes'] = true;
+            if (isset($this->exclude[$token->name])) {
+                $r = true;
+                foreach ($this->exclude[$token->name] as $elem) {
+                    if (!isset($token->attr[$elem])) $r = false;
+                }
+                if ($r) return;
+            }
             if (isset($token->attr['id']) || isset($token->attr['name'])) {
                 return;
             }

tests/HTMLPurifier/Injector/RemoveEmptyTest.php

@@ -91,6 +91,25 @@ class HTMLPurifier_Injector_RemoveEmptyTest extends HTMLPurifier_InjectorHarness
         $this->assertResult('<b>&nbsp;</b>', "<b>\xC2\xA0</b>");
     }
 
+    public function testRemoveIframe()
+    {
+        $this->config->set('HTML.SafeIframe', true);
+        $this->assertResult('<iframe></iframe>', '');
+    }
+
+    public function testNoRemoveIframe()
+    {
+        $this->config->set('HTML.SafeIframe', true);
+        $this->assertResult('<iframe src="http://google.com"></iframe>', '');
+    }
+
+    public function testRemoveDisallowedIframe()
+    {
+        $this->config->set('HTML.SafeIframe', true);
+        $this->config->set('URI.SafeIframeRegexp', '%^http://www.youtube.com/embed/%');
+        $this->assertResult('<iframe src="http://google.com"></iframe>', '');
+    }
+
 }
 
 // vim: et sw=4 sts=4