Support <picture> in image extraction

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.
+    // The main image element. Could be <img>, or <picture> containing <img>.
     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;
     // Cloned and processed element.
-    private ImageElement clonedImg;
+    private Element clonedImg;
 
     /**
      * 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;
         width = w;
         height = h;
         srcUrl = src;
         if (srcUrl == null) {
             srcUrl = "";
         }
     }
 
     private void cloneAndProcessNode() {
-        ImageElement ie = ImageElement.as(Element.as(imgElement.cloneNode(false)));
-        ie.setSrc(srcUrl);
-        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);
+        Element cloned = Element.as(imgElement.cloneNode(true));
+        if (imgElement.getTagName() == "IMG") {
+            ImageElement ie = ImageElement.as(cloned);
+            ie.setSrc(srcUrl);
+            // 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.stripImageElement(ie);
         }
-        DomUtil.makeSrcSetAbsolute(ie);
-        DomUtil.stripImageElement(ie);
+        DomUtil.makeAllSrcAttributesAbsolute(cloned);
+        DomUtil.makeAllSrcSetAbsolute(cloned);
 
-        clonedImg = ie;
+        clonedImg = cloned;
     }
 
     @Override
     public String generateOutput(boolean textOnly) {
         if (textOnly) return "";
         if (clonedImg == null) {
             cloneAndProcessNode();
         }
         return clonedImg.getString();
     }
@@ skipping 25 matching lines @@
     /**
      * 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 List<String> getUrlList() {
         if (clonedImg == null) {
             cloneAndProcessNode();
         }
         List<String> list = new ArrayList<>();
-        list.add(srcUrl);
-        list.addAll(DomUtil.getSrcSetUrls(clonedImg));
+        if (!srcUrl.isEmpty()) {
+            list.add(srcUrl);

[mdjones, 2017/01/17 17:41:47]

nit: this can be in-lined, but it doesn't look like we are doing one-line ifs in
this code. I'll leave that up to you. 

[wychen, 2017/01/18 17:29:54]

Acknowledged.

+        }
+        list.addAll(DomUtil.getAllSrcSetUrls(clonedImg));
         return list;
     }
 
-    protected ImageElement getProcessedNode() {
+    protected Element getProcessedNode() {
         if (clonedImg == null) {
             cloneAndProcessNode();
         }
         return clonedImg;
     }
 }