Support extraction of lazily-loaded images

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\">" +
-            "<img id=\"b\" style=\"align: left\" alt=\"b\" data-dummy=\"c\" src=\"image2\">" +
+            "<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\">" +
@@ skipping 42 matching lines @@
     }
 
     public void testRemoveStyleAttributes() {
         String html =
             "<h1 style=\"font-weight: folder\">" +
                 CONTENT_TEXT +
             "</h1>" +
             "<p style=\"\">" +
                 CONTENT_TEXT +
             "</p>" +
-            "<img style=\"align: left\" src=\"/test.png\">" +
+            "<img style=\"align: left\" data-src=\"/test.png\">" +
             "<table style=\"position: absolute\">" +
                 "<tbody style=\"font-size: 2\">" +
                     "<tr style=\"z-index: 0\">" +
                         "<th style=\"top: 0px\">" + CONTENT_TEXT +
                             "<img style=\"align: left\" src=\"/test.png\">" +
                         "</th>" +
                         "<th style=\"width: 20px\">" + CONTENT_TEXT + "</th>" +
                     "</tr><tr style=\"left: 0\">" +
                         "<td style=\"display: block\">" + CONTENT_TEXT + "</td>" +
                         "<td style=\"color: #123\">" + CONTENT_TEXT + "</td>" +
@@ skipping 490 matching lines @@
             "</p>";
 
         mBody.setInnerHTML(html);
 
         ContentExtractor extractor = new ContentExtractor(mRoot);
         String extractedContent = extractor.extractContent();
         assertEquals(expected,
                 TestUtil.removeAllDirAttributes(extractedContent));
     }
 }