[2.1.3] Refine injector algorithm regarding behavior inside nodes that allow paragraphs inside them

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1423 48356398-32a2-884e-a903-53898d9a118a

NEWS

@@ -19,6 +19,9 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   has 'id' attribute fixed, thanks NykO18 for reporting
 - Fix warning emitted when a non-supported URI scheme is passed to the
   MakeAbsolute URIFilter, thanks NykO18 (again)
+- Further refine AutoParagraph injector. Behavior inside of elements
+  allowing paragraph tags clarified: only inline content delimeted by
+  double newlines (not block elements) are paragraphed.
 . %Core.AcceptFullDocuments renamed to %Core.ConvertDocumentToFragment 
   to better communicate its purpose
 

library/HTMLPurifier/Injector/AutoParagraph.php

@@ -6,20 +6,28 @@ HTMLPurifier_ConfigSchema::define(
     'AutoFormat', 'AutoParagraph', false, 'bool', '
 <p>
   This directive turns on auto-paragraphing, where double newlines are
-  converted in to paragraphs whenever possible. Auto-paragraphing
+  converted in to paragraphs whenever possible. Auto-paragraphing:
-  applies when:
 </p>
 <ul>
-  <li>There are inline elements or text in the root node</li>
+  <li>Always applies to inline elements or text in the root node,</li>
-  <li>There are inline elements or text with double newlines or
+  <li>Applies to inline elements or text with double newlines in nodes
-      block elements in nodes that allow paragraph tags</li>
+      that allow paragraph tags,</li>
-  <li>There are double newlines in paragraph tags</li>
+  <li>Applies to double newlines in paragraph tags</li>
 </ul>
 <p>
   <code>p</code> tags must be allowed for this directive to take effect.
   We do not use <code>br</code> tags for paragraphing, as that is
   semantically incorrect.
 </p>
+<p>
+  To prevent auto-paragraphing as a content-producer, refrain from using
+  double-newlines except to specify a new paragraph or in contexts where
+  it has special meaning (whitespace usually has no meaning except in
+  tags like <code>pre</code>, so this should not be difficult.) To prevent
+  the paragraphing of inline text adjacent to block elements, wrap them
+  in <code>div</code> tags (the behavior is slightly different outside of
+  the root node.)
+</p>
 <p>
   This directive has been available since 2.0.1.
 </p>
@@ -62,19 +70,27 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
                 $ok = false;
                 // test if up-coming tokens are either block or have
                 // a double newline in them
+                $nesting = 0;
                 for ($i = $this->inputIndex + 1; isset($this->inputTokens[$i]); $i++) {
                     if ($this->inputTokens[$i]->type == 'start'){
                         if (!$this->_isInline($this->inputTokens[$i])) {
-                            $ok = true;
+                            // we haven't found a double-newline, and
+                            // we've hit a block element, so don't paragraph
+                            $ok = false;
+                            break;
                         }
-                        break;
+                        $nesting++;
+                    }
+                    if ($this->inputTokens[$i]->type == 'end') {
+                        if ($nesting <= 0) break;
+                        $nesting--;
                     }
-                    if ($this->inputTokens[$i]->type == 'end') break;
                     if ($this->inputTokens[$i]->type == 'text') {
+                        // found it!
                         if (strpos($this->inputTokens[$i]->data, "\n\n") !== false) {
                             $ok = true;
+                            break;
                         }
-                        if (!$this->inputTokens[$i]->is_whitespace) break;
                     }
                 }
                 if ($ok) {

library/HTMLPurifier/Strategy/MakeWellFormed.php

@@ -105,6 +105,8 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             // if all goes well, this token will be passed through unharmed
             $token = $tokens[$this->inputIndex];
             
+            //printTokens($tokens, $this->inputIndex);
+            
             foreach ($this->injectors as $i => $x) {
                 if ($x->skip > 0) $this->injectors[$i]->skip--;
             }

tests/HTMLPurifier/Injector/AutoParagraphTest.php

@@ -194,10 +194,7 @@ Bar</p></div>',
     }
     
     function testNoParagraphSingleInlineNodeInBlockNode() {
-        $this->assertResult(
+        $this->assertResult( '<div><b>Foo</b></div>' );
-'<div><b>Foo</b></div>',
-            '<div><b>Foo</b></div>'
-        );
     }
     
     function testParagraphInBlockquote() {
@@ -277,9 +274,7 @@ Par1
     function testBlockNodeTextDelimeterWithoutDoublespaceInBlockNode() {
         $this->assertResult(
 '<div>Par1
-<div>Par2</div></div>',
+<div>Par2</div></div>'
-'<div><p>Par1
-</p><div>Par2</div></div>'
         );
     }
     
@@ -351,6 +346,30 @@ Par2'
         );
     }
     
+    function testInlineAndBlockTagInDivNoParagraph() {
+        $this->assertResult(
+            '<div><code>bar</code> mmm <pre>asdf</pre></div>'
+        );
+    }
+    
+    function testInlineAndBlockTagInDivNeedingParagraph() {
+        $this->assertResult(
+'<div><code>bar</code> mmm
+
+<pre>asdf</pre></div>',
+'<div><p><code>bar</code> mmm</p><pre>asdf</pre></div>'
+        );
+    }
+    
+    function testTextInlineNodeTextThenDoubleNewlineNeedsParagraph() {
+        $this->assertResult(
+'<div>asdf <code>bar</code> mmm
+
+<pre>asdf</pre></div>',
+'<div><p>asdf <code>bar</code> mmm</p><pre>asdf</pre></div>'
+        );
+    }
+    
     function testErrorNeeded() {
         $this->config->set('HTML', 'Allowed', 'b');
         $this->expectError('Cannot enable AutoParagraph injector because p is not allowed');