Merge pull request #74 from Masterminds/feature/html-parsing-options

HTML parsing options
Masterminds · Feb 9, 2015 · 236faa2 · 236faa2
2 parents dda3253 + a50e919
commit 236faa2
Show file tree

Hide file tree

Showing 4 changed files with 84 additions and 14 deletions.
diff --git a/README.md b/README.md
@@ -76,6 +76,35 @@ $html5->save($dom, 'out.html');
 The `$dom` created by the parser is a full `DOMDocument` object. And the
 `save()` and `saveHTML()` methods will take any DOMDocument.
 
+### Options
+
+It is possible to pass in an array of configuration options when loading
+an HTML5 document.
+
+```php
+// An associative array of options
+$options = array(
+  'option_name' => 'option_value',
+);
+
+// Provide the options to the constructor
+$html5 = new HTML5($options);
+
+$dom = $html5->loadHTML($html);
+```
+
+The following options are supported:
+
+* `encode_entities` (boolean): Indicates that the serializer should aggressively
+  encode characters as entities. Without this, it only encodes the bare
+  minimum.
+* `disable_html_ns` (boolean): Prevents the parser from automatically
+  assigning the HTML5 namespace to the DOM document. This is for
+  non-namespace aware DOM tools.
+* `target_doc` (\DOMDocument): A DOM document that will be used as the
+  destination for the parsed nodes.
+* `implicit_namespaces` (array): An assoc array of namespaces that should be
+  used by the parser. Name is tag prefix, value is NS URI.
 
 ## The Low-Level API
 

diff --git a/RELEASE.md b/RELEASE.md
@@ -1,6 +1,8 @@
 # Release Notes
 
-X.X.X (XXXX-XX-XX)
+2.1.0 (2015-02-01)
+- #74: Added `disable_html_ns` and `target_doc` dom parsing options
+- Unified option names
 - #73: Fixed alphabet, &szlig; now can be detected
 - #75 and #76: Allow whitespace in RCDATA tags
 - #77: Fixed parsing blunder for json embeds

diff --git a/src/HTML5/Parser/DOMTreeBuilder.php b/src/HTML5/Parser/DOMTreeBuilder.php
@@ -38,6 +38,12 @@ class DOMTreeBuilder implements EventHandler
 
     const NAMESPACE_XMLNS = 'http://www.w3.org/2000/xmlns/';
 
+    const OPT_DISABLE_HTML_NS = 'disable_html_ns';
+
+    const OPT_TARGET_DOC = 'target_document';
+
+    const OPT_IMPLICIT_NS = 'implicit_namespaces';
+
     /**
      * Holds the HTML5 element names that causes a namespace switch
      *
@@ -157,22 +163,33 @@ public function __construct($isFragment = false, array $options = array())
     {
         $this->options = $options;
 
-        $impl = new \DOMImplementation();
-        // XXX:
-        // Create the doctype. For now, we are always creating HTML5
-        // documents, and attempting to up-convert any older DTDs to HTML5.
-        $dt = $impl->createDocumentType('html');
-        // $this->doc = \DOMImplementation::createDocument(NULL, 'html', $dt);
-        $this->doc = $impl->createDocument(null, null, $dt);
+        if (isset($options[self::OPT_TARGET_DOC])) {
+            $this->doc = $options[self::OPT_TARGET_DOC];
+        } else {
+            $impl = new \DOMImplementation();
+            // XXX:
+            // Create the doctype. For now, we are always creating HTML5
+            // documents, and attempting to up-convert any older DTDs to HTML5.
+            $dt = $impl->createDocumentType('html');
+            // $this->doc = \DOMImplementation::createDocument(NULL, 'html', $dt);
+            $this->doc = $impl->createDocument(null, null, $dt);
+        }
         $this->errors = array();
 
         $this->current = $this->doc; // ->documentElement;
 
         // Create a rules engine for tags.
         $this->rules = new TreeBuildingRules($this->doc);
 
+        $implicitNS = array();
+        if (isset($this->options[self::OPT_IMPLICIT_NS])) {
+            $implicitNS = $this->options[self::OPT_IMPLICIT_NS];
+        } elseif (isset($this->options["implicitNamespaces"])) {
+            $implicitNS = $this->options["implicitNamespaces"];
+        }
+
         // Fill $nsStack with the defalut HTML5 namespaces, plus the "implicitNamespaces" array taken form $options
-        array_unshift($this->nsStack, (isset($this->options["implicitNamespaces"]) ? $this->options["implicitNamespaces"] : array()) + array(
+        array_unshift($this->nsStack, $implicitNS + array(
             '' => self::NAMESPACE_HTML
         ) + $this->implicitNamespaces);
 
@@ -345,10 +362,10 @@ public function startTag($name, $attributes = array(), $selfClosing = false)
                 $ele = $this->doc->importNode($frag->documentElement, true);
 
             } else {
-                if (isset($this->nsStack[0][$prefix])) {
-                    $ele = $this->doc->createElementNS($this->nsStack[0][$prefix], $lname);
-                } else {
+                if (!isset($this->nsStack[0][$prefix]) || ($prefix === "" && isset($this->options[self::OPT_DISABLE_HTML_NS]) && $this->options[self::OPT_DISABLE_HTML_NS])) {
                     $ele = $this->doc->createElement($lname);
+                } else {
+                    $ele = $this->doc->createElementNS($this->nsStack[0][$prefix], $lname);
                 }
             }
 
@@ -664,4 +681,4 @@ protected function isParent($tagname)
     {
         return $this->current->tagName == $tagname;
     }
-}
+}
diff --git a/test/HTML5/Parser/DOMTreeBuilderTest.php b/test/HTML5/Parser/DOMTreeBuilderTest.php
@@ -55,6 +55,7 @@ public function testDocument()
 
         $this->assertInstanceOf('\DOMDocument', $doc);
         $this->assertEquals('html', $doc->documentElement->tagName);
+        $this->assertEquals('http://www.w3.org/1999/xhtml', $doc->documentElement->namespaceURI);
     }
 
     public function testStrangeCapitalization()
@@ -78,14 +79,35 @@ public function testStrangeCapitalization()
         $this->assertEquals("foo", $xpath->query( "//x:script" )->item( 0 )->nodeValue);
     }
 
+    public function testDocumentWithDisabledNamespaces()
+    {
+        $html = "<!DOCTYPE html><html></html>";
+        $doc = $this->parse($html, array('disable_html_ns' => true));
+
+        $this->assertInstanceOf('\DOMDocument', $doc);
+        $this->assertEquals('html', $doc->documentElement->tagName);
+        $this->assertNull($doc->documentElement->namespaceURI);
+    }
+
+    public function testDocumentWithATargetDocument()
+    {
+        $targetDom = new \DOMDocument();
+
+        $html = "<!DOCTYPE html><html></html>";
+        $doc = $this->parse($html, array('target_document' => $targetDom));
+
+        $this->assertInstanceOf('\DOMDocument', $doc);
+        $this->assertSame($doc, $targetDom);
+        $this->assertEquals('html', $doc->documentElement->tagName);
+    }
+
     public function testDocumentFakeAttrAbsence()
     {
         $html = "<!DOCTYPE html><html xmlns=\"http://www.w3.org/1999/xhtml\"><body>foo</body></html>";
         $doc = $this->parse($html, array('xmlNamespaces'=>true));
 
         $xp = new \DOMXPath($doc);
         $this->assertEquals(0, $xp->query("//@html5-php-fake-id-attribute")->length);
-
     }
 
     public function testFragment()