Add support for figure element

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

Index: java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
diff --git a/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java b/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
index 5b4eb0037ded139f59cadf45ba8df2cb4622e4f6..c879e5bfcb32e960c07d9fe3b54db1366ff6d4cd 100644
--- a/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
+++ b/java/org/chromium/distiller/extractors/embeds/ImageExtractor.java
@@ -4,9 +4,13 @@
 
 package org.chromium.distiller.extractors.embeds;
 
+import com.google.gwt.dom.client.Document;
 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.DomUtil;
 import org.chromium.distiller.LogUtil;
+import org.chromium.distiller.webdocument.WebFigure;
 import org.chromium.distiller.webdocument.WebImage;
 
 import java.util.HashSet;
@@ -18,12 +22,18 @@ import java.util.Set;
  */
 public class ImageExtractor implements EmbedExtractor {
     private static final Set<String> relevantTags = new HashSet<>();
+    private String imgSrc;
+    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");
     }
+
     private static final String[] LAZY_IMAGE_ATTRIBUTES =
-        {"data-src", "data-original", "datasrc", "data-url"};
+            {"data-src", "data-original", "datasrc", "data-url"};
 
     @Override
     public Set<String> getRelevantTagNames() {
@@ -35,38 +45,63 @@ public class ImageExtractor implements EmbedExtractor {
         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();
+        imgSrc = "";
+
         if ("IMG".equals(e.getTagName())) {
-            // This will get the absolute URL of the image and
-            // the displayed image dimension.
-            ImageElement imageElement = ImageElement.as(e);
-            // Try to get lazily-loaded images before falling back to get the src attribute.
-            for(String attr: LAZY_IMAGE_ATTRIBUTES) {
-                imgSrc = imageElement.getAttribute(attr);
-                if (!imgSrc.isEmpty())
-                    break;
-            }
-            if (!imgSrc.isEmpty()) {
-                // We cannot trust the dimension if the image is not loaded yet.
-                // In some cases there are 1x1 placeholder images.
-                width = 0;
-                height = 0;
-            } else {
-                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));
+            return new WebImage(e, width, height, imgSrc);
+        } else if ("FIGURE".equals(e.getTagName())) {
+            Element img = getFirstElementByTagName(e, "IMG");
+            if (img != null) {
+                extractImageAttributes(ImageElement.as(img));
+                Element figcaption = Document.get().createElement("FIGCAPTION");

[wychen, 2016/08/05 02:13:03]

If we need to keep the structure, directly pass the <figcation> element (cap) to
WebFigure(). Otherwise, create a new <figcaption> and use setInnerText(). This
way, we don't use setInnerHTML, and avoid unnecessary copying.

This piece of code is executed for every <figure>, even if they are not
considered content, so we better keep it fast.

+                Element cap = getFirstElementByTagName(e, "FIGCAPTION");
+                if (cap != null) {
+                    if (getFirstElementByTagName(cap, "A") != null) {
+                        figcaption.setInnerHTML(cap.getInnerHTML());
+                    } else {
+                      figcaption.setInnerText(cap.getInnerText());
+                    }
+                } else {
+                    figcaption.setInnerText(e.getInnerText());
+                }
+                return new WebFigure(img, width, height, imgSrc, figcaption);
             }
         }
+        return null;
+    }
 
+    private void extractImageAttributes(ImageElement imageElement) {
+        // This will get the absolute URL of the image and
+        // the displayed image dimension.
+        // Try to get lazily-loaded images before falling back to get the src attribute.
+        for (String attr : LAZY_IMAGE_ATTRIBUTES) {
+            imgSrc = imageElement.getAttribute(attr);
+            if (!imgSrc.isEmpty())
+                break;
+        }
+        if (!imgSrc.isEmpty()) {
+            // We cannot trust the dimension if the image is not loaded yet.
+            // In some cases there are 1x1 placeholder images.
+            width = 0;
+            height = 0;
+        } else {
+            imgSrc = imageElement.getSrc();
+            // As an ImageElement is manipulated here, it is possible
+            // to get the real dimensions.
+            width = imageElement.getWidth();
+            height = imageElement.getHeight();
+        }
         if (LogUtil.isLoggable(LogUtil.DEBUG_LEVEL_VISIBILITY_INFO)) {
             LogUtil.logToConsole("Extracted WebImage: " + imgSrc);
         }
-        return new WebImage(e, width, height, imgSrc);
+    }
+
+    private Element getFirstElementByTagName(Element e, String tagName) {
+        NodeList<Element> elements = e.getElementsByTagName(tagName);
+        if (elements.getLength() > 0) {
+            return elements.getItem(0);
+        }
+        return null;
     }
 }