[2.1.0] Implement Ruby.

- Destroy some zombie context variables
- Reorganize some TODO items

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1347 48356398-32a2-884e-a903-53898d9a118a

TODO

@@ -7,13 +7,12 @@ TODO List
     ? Maybe I'll Do It
 ==========================
 
+If no interest is expressed for a feature that may required a considerable
+amount of effort to implement, it may get endlessly delayed. Do not be
+afraid to cast your vote for the next feature to be implemented!
+
 2.1 release [Refactor, refactor!]
- # URI validation routines tighter (see docs/dev-code-quality.html) (COMPLEX)
- # Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
- # Ruby support
  - Configuration profiles: predefined directives set with one func call
- - Implement IDREF support (harder than it seems, since you cannot have
-   IDREFs to non-existent IDs)
  - Allow non-ASCII characters in font names
  - Explain how to use HTML Purifier in non-PHP languages / create
    a simple command line stub
@@ -39,6 +38,8 @@ TODO List
 
 2.4 release [It's All About Trust] (floating)
  # Implement untrusted, dangerous elements/attributes
+ # Implement IDREF support (harder than it seems, since you cannot have
+   IDREFs to non-existent IDs)
 
 3.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
@@ -77,6 +78,8 @@ Unknown release (on a scratch-an-itch basis)
  - Reorganize Unit Tests
     - Refactor loop tests: Lexer
  - Reorganize configuration directives (Create more namespaces! Get messy!)
+ - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Implement lenient <ruby> child validation
 
 Requested
 

docs/dev-code-quality.txt

@@ -11,8 +11,7 @@ docs/examples/demo.php - ad hoc HTML/PHP soup to the extreme
 
 AttrDef - a lot of duplication, more generic classes need to be created;
 a lot of strtolower() calls, no legit casing
-    Class - doesn't support Unicode characters (fringe); uses regular
+    Class - doesn't support Unicode characters (fringe); uses regular expressions
-        expressions
     Lang - code duplication; premature optimization
     Length - easily mistaken for CSSLength
     URI - multiple regular expressions; missing validation for parts (?)
@@ -22,9 +21,6 @@ ConfigSchema - redefinition is a mess
 Strategy
     FixNesting - cannot bubble nodes out of structures, duplicated checks
         for special-case parent node
-    MakeWellFormed - insufficient automatic closing definitions (check HTML
-        spec for optional end tags, also, closing based on type (block/inline)
-        might be efficient).
     RemoveForeignElements - should be run in parallel with MakeWellFormed
 URIScheme - needs to have callable generic checks
     mailto - doesn't validate emails, doesn't validate querystring

docs/proposal-new-directives.txt

@@ -2,7 +2,8 @@
 Configuration Ideas
 
 Here are some theoretical configuration ideas that we could implement some
-time.  Note the naming convention: %Namespace.Directive
+time.  Note the naming convention: %Namespace.Directive. If you want one
+implemented, give us a ring, and we'll move it up the priority chain.
 
 %Attr.RewriteFragments - if there's %Attr.IDPrefix we may want to transparently
     rewrite the URLs we parse too.  However, we can only do it when it's a pure

library/HTMLPurifier/HTMLModule/Ruby.php

@@ -0,0 +1,28 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+
+/**
+ * XHTML 1.1 Ruby Annotation Module, defines elements that indicate
+ * short runs of text alongside base text for annotation or pronounciation.
+ */
+class HTMLPurifier_HTMLModule_Ruby extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Ruby';
+    
+    function HTMLPurifier_HTMLModule_Ruby() {
+        $this->addElement('ruby', true, 'Inline',
+            'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))',
+            'Common');
+        $this->addElement('rbc', true, false, 'Required: rb', 'Common');
+        $this->addElement('rtc', true, false, 'Required: rt', 'Common');
+        $rb =& $this->addElement('rb', true, false, 'Inline', 'Common');
+        $rb->excludes = array('ruby' => true);
+        $rt =& $this->addElement('rt', true, false, 'Inline', 'Common', array('rbspan' => 'Number'));
+        $rt->excludes = array('ruby' => true);
+        $this->addElement('rp', true, false, 'Optional: #PCDATA', 'Common');
+    }
+    
+}
+

library/HTMLPurifier/HTMLModuleManager.php

@@ -28,6 +28,7 @@ require_once 'HTMLPurifier/HTMLModule/Target.php';
 require_once 'HTMLPurifier/HTMLModule/Scripting.php';
 require_once 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
 require_once 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
+require_once 'HTMLPurifier/HTMLModule/Ruby.php';
 
 // tidy modules
 require_once 'HTMLPurifier/HTMLModule/Tidy.php';
@@ -215,7 +216,7 @@ class HTMLPurifier_HTMLModuleManager
         
         $this->doctypes->register(
             'XHTML 1.1', true,
-            array_merge($common, $xml),
+            array_merge($common, $xml, array('Ruby')),
             array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_XHTMLStrict'), // Tidy_XHTML1_1
             array(),
             '-//W3C//DTD XHTML 1.1//EN',

library/HTMLPurifier/Strategy/ValidateAttributes.php

@@ -46,6 +46,7 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
         }
         
         $context->destroy('IDAccumulator');
+        $context->destroy('CurrentToken');
         
         return $tokens;
     }

tests/HTMLPurifier/ComplexHarness.php

@@ -74,6 +74,7 @@ class HTMLPurifier_ComplexHarness extends HTMLPurifier_Harness
         // setup config 
         if ($this->config) {
             $config = HTMLPurifier_Config::create($this->config);
+            $config->autoFinalize = false;
             $config->loadArray($config_array);
         } else {
             $config = HTMLPurifier_Config::create($config_array);

tests/HTMLPurifier/HTMLModule/RubyTest.php

@@ -0,0 +1,56 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModuleHarness.php';
+
+class HTMLPurifier_HTMLModule_RubyTest extends HTMLPurifier_HTMLModuleHarness
+{
+    
+    function setUp() {
+        parent::setUp();
+        $this->config->set('HTML', 'Doctype', 'XHTML 1.1');
+    }
+    
+    function testBasicUse() {
+        $this->assertResult(
+            '<ruby><rb>WWW</rb><rt>World Wide Web</rt></ruby>'
+        );
+    }
+    
+    function testRPUse() {
+        $this->assertResult(
+            '<ruby><rb>WWW</rb><rp>(</rp><rt>World Wide Web</rt><rp>)</rp></ruby>'
+        );
+    }
+    
+    function testComplexUse() {
+        $this->assertResult(
+'<ruby>
+  <rbc>
+    <rb>10</rb>
+    <rb>31</rb>
+    <rb>2002</rb>
+  </rbc>
+  <rtc>
+    <rt>Month</rt>
+    <rt>Day</rt>
+    <rt>Year</rt>
+  </rtc>
+  <rtc>
+    <rt rbspan="3">Expiration Date</rt>
+  </rtc>
+</ruby>'
+        );
+        
+        /* not implemented
+        function testBackwardsCompat() {
+            $this->assertResult(
+                '<ruby>A<rp>(</rp><rt>aaa</rt><rp>)</rp></ruby>',
+                '<ruby><rb>A</rb><rp>(</rp><rt>aaa</rt><rp>)</rp></ruby>'
+            );
+        }
+        */
+        
+    }
+    
+}
+

tests/HTMLPurifier/Strategy/FixNestingTest.php

@@ -63,12 +63,6 @@ class HTMLPurifier_Strategy_FixNestingTest extends HTMLPurifier_StrategyHarness
           '<span><ins>Not allowed!</ins></span>'
         );
         
-        $this->assertResult( // alt config
-          '<span><ins><div>Not allowed!</div></ins></span>',
-          '<span><ins>&lt;div&gt;Not allowed!&lt;/div&gt;</ins></span>',
-          array('Core.EscapeInvalidChildren' => true)
-        );
-        
         // test block element that has inline content
         $this->assertResult(
           '<h1><ins><div>Not allowed!</div></ins></h1>',
@@ -84,6 +78,12 @@ class HTMLPurifier_Strategy_FixNestingTest extends HTMLPurifier_StrategyHarness
           '<div><ins><del><div>Allowed!</div></del></ins></div>'
         );
         
+        $this->assertResult( // alt config
+          '<span><ins><div>Not allowed!</div></ins></span>',
+          '<span><ins>&lt;div&gt;Not allowed!&lt;/div&gt;</ins></span>',
+          array('Core.EscapeInvalidChildren' => true)
+        );
+        
     }
     
     function testExclusionsIntegration() {

tests/HTMLPurifier/StrategyHarness.php

@@ -6,6 +6,7 @@ class HTMLPurifier_StrategyHarness extends HTMLPurifier_ComplexHarness
 {
     
     function setUp() {
+        parent::setUp();
         $this->func      = 'execute';
         $this->to_tokens = true;
         $this->to_html   = true;

tests/test_files.php

@@ -79,6 +79,7 @@ $test_files[] = 'HTMLPurifier/GeneratorTest.php';
 $test_files[] = 'HTMLPurifier/HTMLDefinitionTest.php';
 $test_files[] = 'HTMLPurifier/HTMLModuleManagerTest.php';
 $test_files[] = 'HTMLPurifier/HTMLModuleTest.php';
+$test_files[] = 'HTMLPurifier/HTMLModule/RubyTest.php';
 $test_files[] = 'HTMLPurifier/HTMLModule/ScriptingTest.php';
 $test_files[] = 'HTMLPurifier/HTMLModule/TidyTest.php';
 $test_files[] = 'HTMLPurifier/IDAccumulatorTest.php';