Extract image URLs in srcset as well

java/org/chromium/distiller/webdocument/WebImage.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.webdocument;
 
 import com.google.gwt.dom.client.Document;
 import com.google.gwt.dom.client.Element;
 import com.google.gwt.dom.client.ImageElement;
 
 import org.chromium.distiller.DomUtil;
 
+import java.util.ArrayList;
+import java.util.List;
+
 /**
  * WebImage represents an image in the WebDocument potentially needing extraction.
  */
 public class WebImage extends WebElement {
     // The main image element.
     Element imgElement;
     // The absolute source of the image.
     private String srcUrl;
     // The original width of the image in pixels.
     private int width;
     // The original height of the image in pixels.
     private int height;
+    // The list of image URLs.
+    private List<String> list;
 
     /**
      * Build an image element.
      * @param e The element detected as an image.
      * @param w The original width of the image.
      * @param h The original height of the image.
      * @param src The source URL of the image being extracted.
      */
     public WebImage(Element e, int w, int h, String src) {
         imgElement = e;
@@ skipping 14 matching lines @@
         ie.setSrc(ie.getSrc());
         // If computed width or height is zero, do not override them
         // to keep them visible.
         if (width > 0 && height > 0) {
             ie.setWidth(width);
             ie.setHeight(height);
         }
         DomUtil.makeSrcSetAbsolute(ie);
         DomUtil.stripImageElement(ie);
 
+        list = new ArrayList<>();
+        list.add(srcUrl);
+        list.addAll(DomUtil.getSrcSetUrls(ie));
+
         Element container = Document.get().createDivElement();
         container.appendChild(ie);
         return container.getInnerHTML();
     }
 
     /**
      * Get the image element of this WebImage.
      * @return Image element or null.
      */
     public Element getImageNode() {
@@ skipping 10 matching lines @@
 
     /**
      * Get the height of this image in pixels.
      * @return The height of this image in pixels.
      */
     public int getHeight() {
         return height;
     }
 
     /**
-     * Get the source URL of this image.
-     * @return Source URL or an empty string.
+     * Get the list of source URLs of this image.
+     * It's more efficient to call after generateOutput().
+     * @return Source URLs or an empty List.
      */
-    public String getSrc() {
-        return srcUrl;
+    public List<String> getUrlList() {
+        if (list == null) {
+            generateOutput(false);

[wychen, 2016/08/01 20:59:20]

This feels entangled. :(

[mdjones, 2016/08/01 21:14:35]

Can we instead cut the top part of generateOutput and put it into a function
called something like cloneAndProcessNode? We could then call that function
lazily in multiple places. Leaving this as-is will cause a lot of confusion
later on.

[wychen, 2016/08/01 21:35:15]

Done.

+        }
+        return list;
     }
 }