merged branch jakzal/domcrawler-namespace-autodiscovery (PR symfony#6650)

fabpot · fabpot · commit 98c0d38a440e · 2013-09-25T08:05:47.000+02:00
This PR was merged into the master branch. Discussion ---------- [DomCrawler] Added auto-discovery and explicit registration of namespaces in filter() and filterByXPath() | Q | A | --- | --- |Bug fix: | no |Feature addition: |yes |Backwards compatibility break: | yes, default namespace is no longer removed in the `addContent` method |Symfony2 tests pass: | yes| |Fixes the following tickets: | symfony#4845 |Todo: | - |License of the code:| MIT |Documentation PR: | symfony/symfony-docs#2979 * added support for automatic discovery and explicit registration of document namespaces for `Crawler::filterXPath()` and `Crawler::filter()` * improved content type guessing in `Crawler::addContent()` * [BC BREAK] `Crawler::addXmlContent()` no longer removes the default document namespace I mentioned in symfony#4845 it would probably be possible to use [DOMNode::lookupNamespaceURI()](http://www.php.net/manual/en/domnode.lookupnamespaceuri.php) to find a namespace URI by given prefix. Unfortunately we cannot use it here since we'd have to call it on a node in the namespace we're looking for. Current implementation makes the following query to find a namespace: ```php $domxpath->query('(//namespace::*[name()="media"])[last()]') ``` Commits ------- 77e2fa5 [DomCrawler] Removed checks if CssSelector is present. 9110468 [DomCrawler] Enabled manual namespace registration. be1e4e6 [DomCrawler] Enabled default namespace prefix overloading. 943d446 [DomCrawler] Updated the CHANGELOG with namespace auto-registration details. c6fbb13 [DomCrawler] Added support for an automatic default namespace registration. 587e2dd [DomCrawler] Made that default namespace is no longer removed when loading documents with addXmlContent(). c905bba [DomCrawler] Added more tests for namespaced filtering. 6e717a3 [DomCrawler] Made sure only the default namespace is removed when loading an XML content. e5b8abb [DomCrawler] Added auto-discovery of namespaces in Crawler::filter() and Crawler::filterByXPath().
diff --git a/src/Symfony/Component/DomCrawler/CHANGELOG.md b/src/Symfony/Component/DomCrawler/CHANGELOG.md
@@ -1,6 +1,15 @@
 CHANGELOG
 =========
 
+2.4.0
+-----
+
+ * added support for automatic discovery and explicit registration of document
+   namespaces for `Crawler::filterXPath()` and `Crawler::filter()`
+ * improved content type guessing in `Crawler::addContent()`
+ * [BC BREAK] `Crawler::addXmlContent()` no longer removes the default document
+   namespace
+
 2.3.0
 -----
 
diff --git a/src/Symfony/Component/DomCrawler/Crawler.php b/src/Symfony/Component/DomCrawler/Crawler.php
@@ -27,6 +27,16 @@ class Crawler extends \SplObjectStorage
      */
     protected $uri;
 
+    /**
+     * @var string The default namespace prefix to be used with XPath and CSS expressions
+     */
+    private $defaultNamespacePrefix = 'default';
+
+    /**
+     * @var array A map of manually registered namespaces
+     */
+    private $namespaces = array();
+
     /**
      * Constructor.
      *
@@ -92,7 +102,7 @@ public function add($node)
     public function addContent($content, $type = null)
     {
         if (empty($type)) {
-            $type = 'text/html';
+            $type = 0 === strpos($content, '<?xml') ? 'application/xml' : 'text/html';
         }
 
         // DOM only for HTML/XML content
@@ -195,9 +205,7 @@ public function addXmlContent($content, $charset = 'UTF-8')
 
         $dom = new \DOMDocument('1.0', $charset);
         $dom->validateOnParse = true;
-
-        // remove the default namespace to make XPath expressions simpler
-        @$dom->loadXML(str_replace('xmlns', 'ns', $content), LIBXML_NONET);
+        @$dom->loadXML($content, LIBXML_NONET);
 
         libxml_use_internal_errors($current);
         libxml_disable_entity_loader($disableEntities);
@@ -579,7 +587,8 @@ public function filterXPath($xpath)
             $root->appendChild($document->importNode($node, true));
         }
 
-        $domxpath = new \DOMXPath($document);
+        $prefixes = $this->findNamespacePrefixes($xpath);
+        $domxpath = $this->createDOMXPath($document, $prefixes);
 
         return new static($domxpath->query($xpath), $this->uri);
     }
@@ -709,6 +718,25 @@ public function form(array $values = null, $method = null)
         return $form;
     }
 
+    /**
+     * Overloads a default namespace prefix to be used with XPath and CSS expressions.
+     *
+     * @param string $prefix
+     */
+    public function setDefaultNamespacePrefix($prefix)
+    {
+        $this->defaultNamespacePrefix = $prefix;
+    }
+
+    /**
+     * @param string $prefix
+     * @param string $namespace
+     */
+    public function registerNamespace($prefix, $namespace)
+    {
+        $this->namespaces[$prefix] = $namespace;
+    }
+
     /**
      * Converts string for XPath expressions.
      *
@@ -792,4 +820,62 @@ protected function sibling($node, $siblingDir = 'nextSibling')
 
         return $nodes;
     }
+
+    /**
+     * @param \DOMDocument $document
+     * @param array        $prefixes
+     *
+     * @return \DOMXPath
+     *
+     * @throws \InvalidArgumentException
+     */
+    private function createDOMXPath(\DOMDocument $document, array $prefixes = array())
+    {
+        $domxpath = new \DOMXPath($document);
+
+        foreach ($prefixes as $prefix) {
+            $namespace = $this->discoverNamespace($domxpath, $prefix);
+            $domxpath->registerNamespace($prefix, $namespace);
+        }
+
+        return $domxpath;
+    }
+
+    /**
+     * @param \DOMXPath $domxpath
+     * @param string    $prefix
+     *
+     * @return string
+     *
+     * @throws \InvalidArgumentException
+     */
+    private function discoverNamespace(\DOMXPath $domxpath, $prefix)
+    {
+        if (isset($this->namespaces[$prefix])) {
+            return $this->namespaces[$prefix];
+        }
+
+        // ask for one namespace, otherwise we'd get a collection with an item for each node
+        $namespaces = $domxpath->query(sprintf('(//namespace::*[name()="%s"])[last()]', $this->defaultNamespacePrefix === $prefix ? '' : $prefix));
+
+        if ($node = $namespaces->item(0)) {
+            return $node->nodeValue;
+        }
+
+        throw new \InvalidArgumentException(sprintf('Could not find a namespace for the prefix: "%s"', $prefix));
+    }
+
+    /**
+     * @param $xpath
+     *
+     * @return array
+     */
+    private function findNamespacePrefixes($xpath)
+    {
+        if (preg_match_all('/(?P<prefix>[a-zA-Z_][a-zA-Z_0-9\-\.]*):[^:]/', $xpath, $matches)) {
+            return array_unique($matches['prefix']);
+        }
+
+        return array();
+    }
 }
diff --git a/src/Symfony/Component/DomCrawler/Tests/CrawlerTest.php b/src/Symfony/Component/DomCrawler/Tests/CrawlerTest.php
@@ -11,6 +11,7 @@
 
 namespace Symfony\Component\DomCrawler\Tests;
 
+use Symfony\Component\CssSelector\CssSelector;
 use Symfony\Component\DomCrawler\Crawler;
 
 class CrawlerTest extends \PHPUnit_Framework_TestCase
@@ -370,6 +371,55 @@ public function testFilterXPath()
         $this->assertCount(6, $crawler->filterXPath('//li'), '->filterXPath() filters the node list with the XPath expression');
     }
 
+    public function testFilterXPathWithDefaultNamespace()
+    {
+        $crawler = $this->createTestXmlCrawler()->filterXPath('//default:entry/default:id');
+        $this->assertCount(1, $crawler, '->filterXPath() automatically registers a namespace');
+        $this->assertSame('tag:youtube.com,2008:video:kgZRZmEc9j4', $crawler->text());
+    }
+
+    public function testFilterXPathWithCustomDefaultNamespace()
+    {
+        $crawler = $this->createTestXmlCrawler();
+        $crawler->setDefaultNamespacePrefix('x');
+        $crawler = $crawler->filterXPath('//x:entry/x:id');
+
+        $this->assertCount(1, $crawler, '->filterXPath() lets to override the default namespace prefix');
+        $this->assertSame('tag:youtube.com,2008:video:kgZRZmEc9j4', $crawler->text());
+    }
+
+    public function testFilterXPathWithNamespace()
+    {
+        $crawler = $this->createTestXmlCrawler()->filterXPath('//yt:accessControl');
+        $this->assertCount(2, $crawler, '->filterXPath() automatically registers a namespace');
+    }
+
+    public function testFilterXPathWithMultipleNamespaces()
+    {
+        $crawler = $this->createTestXmlCrawler()->filterXPath('//media:group/yt:aspectRatio');
+        $this->assertCount(1, $crawler, '->filterXPath() automatically registers multiple namespaces');
+        $this->assertSame('widescreen', $crawler->text());
+    }
+
+    /**
+     * @expectedException        \InvalidArgumentException
+     * @expectedExceptionMessage Could not find a namespace for the prefix: "foo"
+     */
+    public function testFilterXPathWithAnInvalidNamespace()
+    {
+        $this->createTestXmlCrawler()->filterXPath('//media:group/foo:aspectRatio');
+    }
+
+    public function testFilterXPathWithManuallyRegisteredNamespace()
+    {
+        $crawler = $this->createTestXmlCrawler();
+        $crawler->registerNamespace('m', 'http://search.yahoo.com/mrss/');
+
+        $crawler = $crawler->filterXPath('//m:group/yt:aspectRatio');
+        $this->assertCount(1, $crawler, '->filterXPath() uses manually registered namespace');
+        $this->assertSame('widescreen', $crawler->text());
+    }
+
     /**
      * @covers Symfony\Component\DomCrawler\Crawler::filter
      */
@@ -384,6 +434,30 @@ public function testFilter()
         $this->assertCount(6, $crawler->filter('li'), '->filter() filters the node list with the CSS selector');
     }
 
+    public function testFilterWithDefaultNamespace()
+    {
+        $crawler = $this->createTestXmlCrawler()->filter('default|entry default|id');
+        $this->assertCount(1, $crawler, '->filter() automatically registers namespaces');
+        $this->assertSame('tag:youtube.com,2008:video:kgZRZmEc9j4', $crawler->text());
+    }
+
+    public function testFilterWithNamespace()
+    {
+        CssSelector::disableHtmlExtension();
+
+        $crawler = $this->createTestXmlCrawler()->filter('yt|accessControl');
+        $this->assertCount(2, $crawler, '->filter() automatically registers namespaces');
+    }
+
+    public function testFilterWithMultipleNamespaces()
+    {
+        CssSelector::disableHtmlExtension();
+
+        $crawler = $this->createTestXmlCrawler()->filter('media|group yt|aspectRatio');
+        $this->assertCount(1, $crawler, '->filter() automatically registers namespaces');
+        $this->assertSame('widescreen', $crawler->text());
+    }
+
     public function testSelectLink()
     {
         $crawler = $this->createTestCrawler();
@@ -656,6 +730,22 @@ public function createTestCrawler($uri = null)
         return new Crawler($dom, $uri);
     }
 
+    protected function createTestXmlCrawler($uri = null)
+    {
+        $xml = '<?xml version="1.0" encoding="UTF-8"?>
+            <entry xmlns="http://www.w3.org/2005/Atom" xmlns:media="http://search.yahoo.com/mrss/" xmlns:yt="http://gdata.youtube.com/schemas/2007">
+                <id>tag:youtube.com,2008:video:kgZRZmEc9j4</id>
+                <yt:accessControl action="comment" permission="allowed"/>
+                <yt:accessControl action="videoRespond" permission="moderated"/>
+                <media:group>
+                    <media:title type="plain">Chordates - CrashCourse Biology #24</media:title>
+                    <yt:aspectRatio>widescreen</yt:aspectRatio>
+                </media:group>
+            </entry>';
+
+        return new Crawler($xml, $uri);
+    }
+
     protected function createDomDocument()
     {
         $dom = new \DOMDocument();
