Fix final content and title extraction.

test/com/dom_distiller/client/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 com.dom_distiller.client;
+
+import com.google.gwt.dom.client.Document;
+import com.google.gwt.dom.client.Element;
+import com.google.gwt.junit.client.GWTTestCase;
+
+public class ContentExtractorTest extends GWTTestCase {
+    private static final String CONTENT_TEXT = "Lorem Ipsum Lorem Ipsum Lorem Ipsum.";
+    private static final String TITLE_TEXT = "I am the document title";
+
+    @Override
+    public String getModuleName() {
+        return "com.dom_distiller.DomDistillerJUnit";
+    }
+
+    public void testDoesNotExtractTitle() {
+        Element root = Document.get().getDocumentElement();
+        root.appendChild(TestUtil.createTitle(TITLE_TEXT));
+        Document.get().setTitle(TITLE_TEXT);
+
+        Element body = Document.get().createElement("body");
+        root.appendChild(body);
+
+        Element titleDiv = TestUtil.createDiv(0);
+        titleDiv.appendChild(TestUtil.createText(TITLE_TEXT));
+        body.appendChild(titleDiv);
+        Element contentDiv = TestUtil.createDiv(1);
+        contentDiv.appendChild(TestUtil.createText(CONTENT_TEXT));
+        body.appendChild(contentDiv);
+
+        contentDiv = TestUtil.createDiv(2);
+        contentDiv.appendChild(TestUtil.createText(CONTENT_TEXT));
+        body.appendChild(contentDiv);
+
+        contentDiv = TestUtil.createDiv(3);
+        contentDiv.appendChild(TestUtil.createText(CONTENT_TEXT));
+
+        body.appendChild(contentDiv);
+
+        String extractedContent = ContentExtractor.extractContent();

[cjhopman, 2014/05/22 00:27:21]

Could we confirm that this isn't extracted because it's the title. Something
like:

Setup (without Document.get.setTitle())
extractContent()
check extracted content
Document.get().setTitle(TITLE_TEXT)
extractContent()
check extracted content

[Yaron, 2014/05/22 17:05:24]

Done.

+        assertTrue(extractedContent + " must contain 'content':" + CONTENT_TEXT,
+                extractedContent.contains(contentDiv.getInnerText()));
+        assertFalse(
+                extractedContent + " must not contain 'title':" +TITLE_TEXT,
+                extractedContent.contains(titleDiv.getInnerText()));
+    }
+}