Process ordered list items as a single WebText

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 121 matching lines @@
         outerFontTag.appendChild(TestUtil.createText(" "));
 
         ContentExtractor extractor = new ContentExtractor(mRoot);
         String extractedContent = extractor.extractContent();
         assertEquals("<font><span><font>" + CONTENT_TEXT + "</font></span> " +
                      "<span><font>" + CONTENT_TEXT + "</font></span>\n" +
                      "<span><font>" + CONTENT_TEXT + "</font></span> </font>",
                 TestUtil.removeAllDirAttributes(extractedContent));
     }
 
+    public void testPreserveOrderedList() {
+        Element outerListTag = Document.get().createElement("OL");
+        mBody.appendChild(outerListTag);
+
+        outerListTag.appendChild(TestUtil.createListItem(CONTENT_TEXT));
+        outerListTag.appendChild(TestUtil.createListItem(CONTENT_TEXT));
+        outerListTag.appendChild(TestUtil.createListItem(CONTENT_TEXT));
+        outerListTag.appendChild(TestUtil.createListItem(CONTENT_TEXT));
+
+        ContentExtractor extractor = new ContentExtractor(mRoot);
+        String extractedContent = extractor.extractContent();
+        assertEquals("<ol>" +
+                     "<li>" + CONTENT_TEXT + "</li>" +
+                     "<li>" + CONTENT_TEXT + "</li>" +
+                     "<li>" + CONTENT_TEXT + "</li>" +
+                     "<li>" + CONTENT_TEXT + "</li>" +
+                     "</ol>",
+                     TestUtil.removeAllDirAttributes(extractedContent));
+    }
+
     private void assertExtractor(String expected, String html) {
         mBody.setInnerHTML("");
         Element div = TestUtil.createDiv(0);
         mBody.appendChild(div);
 
         div.setInnerHTML(html);
         ContentExtractor extractor = new ContentExtractor(mRoot);
         String extractedContent = extractor.extractContent();
         assertEquals(expected, TestUtil.removeAllDirAttributes(extractedContent));
     }
@@ skipping 76 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);
     }
 }