comment + link extraction

[stapibas.git] / src / stapibas / Content / Extractor / Comment.php

diff --git a/src/stapibas/Content/Extractor/Comment.php b/src/stapibas/Content/Extractor/Comment.php
index 4c848c0934c29479be68ae0fc614c1c8febb34fe..ce7403c8d1959a1cc5a04469774bbf9d4af8a657 100644 (file)
--- a/src/stapibas/Content/Extractor/Comment.php
+++ b/src/stapibas/Content/Extractor/Comment.php
@@ -1,13 +1,8 @@
 <?php
 namespace stapibas;
 
-class Content_Extractor_Comment
+class Content_Extractor_Comment extends Content_Extractor_Base
 {
-    public function __construct(Logger $log)
-    {
-        $this->log = $log;
-    }
-
     /**
      * Try to extract comment data from HTML
      *
@@ -22,7 +17,7 @@ class Content_Extractor_Comment
         $xpath = $this->getXpath($doc);
         $hentries = $xpath->query(
             '//*[(' . $this->xpc('h-entry') . ' or ' . $this->xpc('hentry') . ') and '
-            . '//a['
+            . '//*[(self::a or self::h:a) and '
             . $this->xpc('u-in-reply-to') . ' and @href=' . $this->xpq($target)
             . ']'
             . ']'
@@ -38,7 +33,7 @@ class Content_Extractor_Comment
         );
         $hentry = $hentries->item(0);
 
-        $this->extractAuthorData($hentry, $xpath, $data, $doc);
+        $this->extractAuthorData($hentry, $xpath, $data, $source);
         $content = $this->getFirst(
             './/*[' . $this->xpc('e-content') . ']', false, $hentry, $xpath
         );
@@ -51,84 +46,5 @@ class Content_Extractor_Comment
 
         return $data;
     }
-
-    protected function extractAuthorData($hentry, $xpath, &$data, $d)
-    {
-        $data['author_name']  = null;
-        $data['author_image'] = null;
-        $data['author_url']   = null;
-
-        $authors = $xpath->evaluate(
-            './/*[' . $this->xpc('p-author') . ']'
-        );
-        if ($authors->length != 1) {
-            return false;
-        }
-
-        $author = $authors->item(0);
-
-        $data['author_name'] = $this->getFirst(
-            './/*[' . $this->xpc('p-name') . ' or ' . $this->xpc('fn') . ']',
-            null, $author, $xpath
-        );
-        $data['author_image'] = $this->getFirst(
-            './/*[' . $this->xpc('u-photo') . ']',
-            'src', $author, $xpath
-        );
-        $data['author_url'] = $this->getFirst(
-            './/*[' . $this->xpc('u-url') . ']',
-            'href', $author, $xpath
-        );
-    }
-
-    protected function getFirst($xpathExpr, $attrName, $elem, $xpath)
-    {
-        $items = $xpath->evaluate($xpathExpr, $elem);
-        if (!$items instanceof \DOMNodeList || $items->length == 0) {
-            return null;
-        }
-
-        if ($attrName === false) {
-            return $items->item(0);
-        } else if ($attrName == null) {
-            return $items->item(0)->nodeValue;
-        } else {
-            return $items->item(0)->attributes->getNamedItem($attrName)->nodeValue;
-        }
-    }
-
-    protected function innerHtml($element)
-    {
-        $innerHTML = '';
-        $children = $element->childNodes;
-        foreach ($children as $child) {
-            $tmp_dom = new \DOMDocument();
-            $tmp_dom->appendChild($tmp_dom->importNode($child, true));
-            $innerHTML .= rtrim($tmp_dom->saveHTML(), "\n");
-        }
-        return trim($innerHTML);
-    }
-
-    protected function getXpath($node)
-    {
-        $xpath = new \DOMXPath($node);
-        $xpath->registerNamespace('h', 'http://www.w3.org/1999/xhtml');
-        return $xpath;
-    }
-
-    protected function xpc($class)
-    {
-        return 'contains('
-            . 'concat(" ", normalize-space(@class), " "),'
-            . '" ' . $class . ' "'
-            . ')';
-    }
-
-    protected function xpq($str)
-    {
-        return '"' . htmlspecialchars($str, ENT_QUOTES) . '"';
-    }
-
 }
-
 ?>