Support <picture> in image extraction

javatests/org/chromium/distiller/ContentExtractorTest.java

 // Copyright 2014 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;
 
 import com.google.gwt.dom.client.Document;
 import com.google.gwt.dom.client.Element;
 
 public class ContentExtractorTest extends DomDistillerJsTestCase {
@@ skipping 76 matching lines @@
     }
 
     public void testImage() {
         // Test the absolute and different kinds of relative URLs for image sources,
         // and also add an extra comma (,) as malformed srcset syntax for robustness.
         // Also test images in WebImage and WebTable.
         // TODO(wychen): add images in WebText when it is supported.
         final String html =
             "<h1>" + CONTENT_TEXT + "</h1>" +
             "<img id=\"a\" style=\"typo\" align=\"left\" src=\"image\" srcset=\"image200 200w, //example.org/image400 400w\">" +
+            "<figure><picture>" +
+                "<source srcset=\"image200 200w, //example.org/image400 400w\">" +
+                "<source srcset=\"image100 100w, //example.org/image300 300w\">" +
+                "<img>" +
+            "</picture></figure>" +
             "<img id=\"b\" style=\"align: left\" alt=\"b\" data-dummy=\"c\" data-src=\"image2\">" +
             "<table role=\"grid\"><tbody><tr><td>" +
                 "<img id=\"c\" style=\"a\" alt=\"b\" src=\"/image\" srcset=\"https://example.com/image2x 2x, /image4x 4x,\">" +
                 "<img id=\"d\" style=\"a\" align=\"left\" src=\"/image2\">" +
                 "</td></tr></tbody></table>" +
             "<p>" + CONTENT_TEXT + "</p>";
 
         final String expected =
             "<h1>" + CONTENT_TEXT + "</h1>" +
             "<img src=\"http://example.com/path/image\" " +
                  "srcset=\"http://example.com/path/image200 200w, http://example.org/image400 400w\">" +
+            "<figure><picture>" +
+                "<source srcset=\"http://example.com/path/image200 200w, http://example.org/image400 400w\">" +
+                "<source srcset=\"http://example.com/path/image100 100w, http://example.org/image300 300w\">" +
+                "<img>" +
+            "</picture></figure>" +
             "<img alt=\"b\" src=\"http://example.com/path/image2\">" +
             "<table role=\"grid\"><tbody><tr><td>" +
                 "<img alt=\"b\" src=\"http://example.com/image\" " +
                      "srcset=\"https://example.com/image2x 2x, http://example.com/image4x 4x, \">" +
                 "<img src=\"http://example.com/image2\">" +
             "</td></tr></tbody></table>" +
             "<p>" + CONTENT_TEXT + "</p>";
 
         mHead.setInnerHTML("<base href=\"http://example.com/path/\">");
         mBody.setInnerHTML(html);
@@ skipping 563 matching lines @@
 
         final String expected =
             "<p>" + CONTENT_TEXT + "</p>" +
             "<p>" + CONTENT_TEXT + "</p>" +
             "<p>" + CONTENT_TEXT + "</p>" +
             "<p>" + CONTENT_TEXT + "</p>";
 
         assertExtractor(expected, html);
     }
 }