Implement %AutoFormat.RemoveEmpty.RemoveNbsp, by popular demand.

Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>

NEWS

@@ -20,6 +20,10 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 ! Implement %HTML.Attr.Name.UseCDATA, which relaxes validation rules on
   the name attribute when set. Use with care. Thanks Ian Cook for
   sponsoring.
+! Implement %AutoFormat.RemoveEmpty.RemoveNbsp, which removes empty
+  tags that contain non-breaking spaces as well other whitespace. You
+  can also modify which tags should have   maintained with
+  %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.
 
 3.3.0, released 2009-02-16
 ! Implement CSS property 'overflow' when %CSS.AllowTricky is true.

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt

@@ -0,0 +1,11 @@
+AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions
+TYPE: lookup
+VERSION: 4.0.0
+DEFAULT: array('td' => true, 'th' => true)
+--DESCRIPTION--
+<p>
+  When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp
+  are enabled, this directive defines what HTML elements should not be
+  removede if they have only a non-breaking space in them.
+</p>
+--# vim: et sw=4 sts=4

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

@@ -0,0 +1,15 @@
+AutoFormat.RemoveEmpty.RemoveNbsp
+TYPE: bool
+VERSION: 4.0.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  When enabled, HTML Purifier will treat any elements that contain only
+  non-breaking spaces as well as regular whitespace as empty, and remove
+  them when %AutoForamt.RemoveEmpty is enabled.
+</p>
+<p>
+  See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements
+  that don't have this behavior applied to them.
+</p>
+--# vim: et sw=4 sts=4

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

@@ -31,7 +31,8 @@ DEFAULT: false
 </p>
 <p>
   Elements that contain only whitespace will be treated as empty. Non-breaking
-  spaces, however, do not count as whitespace.
+  spaces, however, do not count as whitespace. See
+  %AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior.
 </p>
 <p>
   This algorithm is not perfect; you may still notice some empty tags,
@@ -39,7 +40,7 @@ DEFAULT: false
   because they were not permitted in that context, or tags that, after
   being auto-closed by another tag, where empty. This is for safety reasons
   to prevent clever code from breaking validation. The general rule of thumb:
-  if a tag looked empty on the way end, it will get removed; if HTML Purifier
+  if a tag looked empty on the way in, it will get removed; if HTML Purifier
   made it empty, it will stay.
 </p>
 --# vim: et sw=4 sts=4

library/HTMLPurifier/Injector/RemoveEmpty.php

@@ -3,12 +3,14 @@
 class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
 {
 
-    private $context, $config;
+    private $context, $config, $attrValidator, $removeNbsp, $removeNbspExceptions;
 
     public function prepare($config, $context) {
         parent::prepare($config, $context);
         $this->config = $config;
         $this->context = $context;
+        $this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp');
+        $this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions');
         $this->attrValidator = new HTMLPurifier_AttrValidator();
     }
 
@@ -17,7 +19,14 @@ class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
         $next = false;
         for ($i = $this->inputIndex + 1, $c = count($this->inputTokens); $i < $c; $i++) {
             $next = $this->inputTokens[$i];
-            if ($next instanceof HTMLPurifier_Token_Text && $next->is_whitespace) continue;
+            if ($next instanceof HTMLPurifier_Token_Text) {
+                if ($next->is_whitespace) continue;
+                if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) {
+                    $plain = str_replace("\xC2\xA0", "", $next->data);
+                    $isWsOrNbsp = $plain === '' || ctype_space($plain);
+                    if ($isWsOrNbsp) continue;
+                }
+            }
             break;
         }
         if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) {

library/HTMLPurifier/Strategy/MakeWellFormed.php

@@ -72,6 +72,8 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
         $custom_injectors = $injectors['Custom'];
         unset($injectors['Custom']); // special case
         foreach ($injectors as $injector => $b) {
+            // XXX: Fix with a legitimate lookup table of enabled filters
+            if (strpos($injector, '.') !== false) continue;
             $injector = "HTMLPurifier_Injector_$injector";
             if (!$b) continue;
             $this->injectors[] = new $injector;

tests/HTMLPurifier/Injector/RemoveEmptyTest.php

@@ -54,6 +54,27 @@ class HTMLPurifier_Injector_RemoveEmptyTest extends HTMLPurifier_InjectorHarness
         $this->assertResult('<b> <i> <u> </u> </i> </b>', '');
     }
 
+    function testRemoveNbsp() {
+        $this->config->set('AutoFormat.RemoveEmpty.RemoveNbsp', true);
+        $this->assertResult('<b>&nbsp;</b>', '');
+    }
+
+    function testRemoveNbspMix() {
+        $this->config->set('AutoFormat.RemoveEmpty.RemoveNbsp', true);
+        $this->assertResult('<b>&nbsp;   &nbsp;</b>', '');
+    }
+
+    function testDontRemoveNbsp() {
+        $this->config->set('AutoFormat.RemoveEmpty.RemoveNbsp', true);
+        $this->assertResult('<td>&nbsp;</b>', "<td>\xC2\xA0</td>");
+    }
+
+    function testRemoveNbspExceptionsSpecial() {
+        $this->config->set('AutoFormat.RemoveEmpty.RemoveNbsp', true);
+        $this->config->set('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions', 'b');
+        $this->assertResult('<b>&nbsp;</b>', "<b>\xC2\xA0</b>");
+    }
+
 }
 
 // vim: et sw=4 sts=4