Add support for figure element

java/org/chromium/distiller/extractors/embeds/ImageExtractor.java

 // Copyright 2015 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 package org.chromium.distiller.extractors.embeds;
 
 import com.google.gwt.dom.client.Element;
 import com.google.gwt.dom.client.ImageElement;
+import com.google.gwt.dom.client.NodeList;
+import org.chromium.distiller.webdocument.WebFigure;

[wychen, 2016/05/31 21:28:04]

Forget to upload this one?

 import org.chromium.distiller.webdocument.WebImage;
 
 import java.util.HashSet;
 import java.util.Set;
 
 /**
  * This class treats images as another type of embed and provides heuristics for lead image
  * candidacy.
  */
 public class ImageExtractor implements EmbedExtractor {
     private static final Set<String> relevantTags = new HashSet<>();
+    private String src;
+    private String caption;
+    private int width;
+    private int height;
+
     static {
         // TODO(mdjones): Add "DIV" to this list for css images and possibly captions.
         relevantTags.add("IMG");
+        relevantTags.add("FIGURE");
     }
 
     @Override
     public Set<String> getRelevantTagNames() {
         return relevantTags;
     }
 
     @Override
     public WebImage extract(Element e) {
         if (!relevantTags.contains(e.getTagName())) {
             return null;
         }
-        String imgSrc = "";
         // Getting OffSetWidth/Height as default values, even they are
         // affected by padding, border, etc.
-        int width = e.getOffsetWidth();
-        int height = e.getOffsetHeight();
+        width = e.getOffsetWidth();
+        height = e.getOffsetHeight();
+        src = "";
+        caption = "";
+
         if ("IMG".equals(e.getTagName())) {
-            // This will get the absolute URL of the image and
-            // the displayed image dimension.
-            ImageElement imageElement = ImageElement.as(e);
-            imgSrc = imageElement.getSrc();
-            // As an ImageElement is manipulated here, it is possible
-            // to get the real dimensions.
-            width = imageElement.getWidth();
-            height = imageElement.getHeight();
+            extractImageAttributes(ImageElement.as(e));
+        } else if ("FIGURE".equals(e.getTagName())) {
+            Element img = getElementByTagName(e, "IMG");
+            if (img != null) {

[wychen, 2016/05/31 21:28:04]

If a malformed <figure> contains no <img>s, an empty WebImage is still returned.

[marcelorcorrea, 2016/05/31 21:46:44]

Done.

+                extractImageAttributes(ImageElement.as(img));
+                Element cap = getElementByTagName(e, "FIGCAPTION");
+                if (cap != null) {
+                    caption = cap.getInnerText();
+                }
+                return new WebFigure(img, width, height, src, caption);
+            }
         }
+        return new WebImage(e, width, height, src);
+    }
 
-        return new WebImage(e, width, height, imgSrc);
+    private void extractImageAttributes(ImageElement img) {
+        src = img.getSrc();
+        width = img.getWidth();
+        height = img.getHeight();
+    }
+
+    private Element getElementByTagName(Element e, String tagName) {

[wychen, 2016/05/31 21:28:04]

getFirstElementByTagName?

[marcelorcorrea, 2016/05/31 21:46:44]

Done.

+        NodeList<Element> elements = e.getElementsByTagName(tagName);
+        if (elements.getLength() > 0) {
+            return elements.getItem(0);
+        }
+        return null;
     }
 }