Clean up attributes of image elements

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 68 matching lines @@
         assertTrue(parser != null);
         assertEquals(MARKUP_PARSER_TITLE, parser.getTitle());
 
         Document.get().setTitle(TITLE_TEXT);
 
         ContentExtractor extractor = new ContentExtractor(mRoot);
         assertEquals("OpenGraph title should be picked over document.title",
                 MARKUP_PARSER_TITLE, extractor.extractTitle());
     }
 
-    public void testImageWithSrcset() {
+    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, WebText, and WebTable.

[wychen, 2015/12/09 05:17:40]

TODO(wychen): how do I get images inside a WebText?

[mdjones, 2015/12/09 17:40:16]

This is an unsolved problem. Since tables are currently treated as a singular
element, it can be argued that we simply ignore images contained in them, or at
least leave them unaltered. If we decide to start traversing into tables, we
would have to make a number of changes to our extraction logic and possibly eval
data. A mix of both is complicated; we can discuss this more offline.

         final String html =
             "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<img src=\"image\" srcset=\"image200 200w, //example.org/image400 400w\">" +
+            "<img id=\"a\" style=\"a\" align=\"left\" src=\"image\" srcset=\"image200 200w, //example.org/image400 400w\">" +
+            "<img id=\"a\" style=\"a\" align=\"left\" src=\"image2\">" +
             "<table role=\"grid\"><tbody><tr><td>" +
-                "<img src=\"/image\" srcset=\"https://example.com/image2x 2x, /image4x 4x,\">" +
+                "<img id=\"a\" style=\"a\" align=\"left\" src=\"/image\" srcset=\"https://example.com/image2x 2x, /image4x 4x,\">" +
+                "<img id=\"a\" 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\">" +
+            "<img src=\"http://example.com/path/image2\">" +
             "<table role=\"grid\"><tbody><tr><td>" +
                 "<img 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);
 
         ContentExtractor extractor = new ContentExtractor(mRoot);
         String extractedContent = extractor.extractContent();
 
         assertEquals(expected,
@@ skipping 27 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\">" +
             "<table style=\"position: absolute\">" +
                 "<tbody style=\"font-size: 2\">" +
                     "<tr style=\"z-index: 0\">" +
-                        "<th style=\"top: 0px\">" + CONTENT_TEXT + "</th>" +
+                        "<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>" +
                     "</tr>" +
                 "</tbody>" +
             "</table>";
 
         final String expected =
             "<h1>" +
                 CONTENT_TEXT +
             "</h1>" +
             "<p>" +
                 CONTENT_TEXT +
             "</p>" +
+            "<img src=\"http://example.com/test.png\">" +
             "<table>" +
                 "<tbody>" +
                     "<tr>" +
-                        "<th>" + CONTENT_TEXT + "</th>" +
+                        "<th>" + CONTENT_TEXT +
+                            "<img src=\"http://example.com/test.png\">" +
+                        "</th>" +
                         "<th>" + CONTENT_TEXT + "</th>" +
                     "</tr><tr>" +
                         "<td>" + CONTENT_TEXT + "</td>" +
                         "<td>" + CONTENT_TEXT + "</td>" +
                     "</tr>" +
                 "</tbody>" +
             "</table>";
 
+        mHead.setInnerHTML("<base href=\"http://example.com/\">");
         mBody.setInnerHTML(html);
 
         ContentExtractor extractor = new ContentExtractor(mRoot);
         String extractedContent = extractor.extractContent();
         assertEquals(expected,
                 TestUtil.removeAllDirAttributes(extractedContent));
     }
 
     public void testPreserveOrderedList() {
         Element outerListTag = Document.get().createElement("OL");
@@ skipping 379 matching lines @@
 
         final String htmlArticle =
             "<h1>" + CONTENT_TEXT + "</h1>" +
             "<div itemscope itemtype=\"http://schema.org/Movie\">" + article + "</div>";
         final String expected = "<h1>" + CONTENT_TEXT + "</h1>" + article;
 
         // Non-article schema.org types should not use the fast path.
         assertExtractor(expected, htmlArticle);
     }
 }