Discard hidden articles when using fast path

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 538 matching lines @@
         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));
     }
 
-    public void testOnlyProcessArticleElement() {
-        final String article = "<p>" + CONTENT_TEXT + "</p><p>" + CONTENT_TEXT + "</p>";
-
-        final String html = "<h1>" + CONTENT_TEXT + "</h1><div>" + article + "</div>";
-        final String expected = "<h1>" + CONTENT_TEXT + "</h1>" + article;
-
-        // Make sure everything is there before using the fast path.
-        assertExtractor(expected, html);
-
-        final String htmlArticle =
-            "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<article>" + article + "</article>";
-
-        assertExtractor(article, htmlArticle);
-    }
-
-    public void testOnlyProcessArticleElementMultiple() {
-        final String article = "<p>" + CONTENT_TEXT + "</p><p>" + CONTENT_TEXT + "</p>";
-
-        final String htmlArticle =
-            "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<article>" + article + "</article>" +
-            "<article>" + article + "</article>";
-        final String expected = "<h1>" + CONTENT_TEXT + "</h1>" + article + article;
-
-        // The existence of multiple articles disables the fast path.
-        assertExtractor(expected, htmlArticle);
-    }
-
-    public void testOnlyProcessOGArticle() {
-        final String article = "<p>" + CONTENT_TEXT + "</p><p>" + CONTENT_TEXT + "</p>";
-
-        final String htmlArticle =
-            "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<div itemscope itemtype=\"http://schema.org/Article\">" + article + "</div>";
-
-        assertExtractor(article, htmlArticle);
-    }
-
-    public void testOnlyProcessOGArticleNews() {
-        final String article = "<p>" + CONTENT_TEXT + "</p><p>" + CONTENT_TEXT + "</p>";
-
-        final String htmlArticle =
-            "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<div itemscope itemtype=\"http://schema.org/NewsArticle\">" + article + "</div>";
-
-        assertExtractor(article, htmlArticle);
-    }
-
-    public void testOnlyProcessOGArticleBlog() {
-        final String article = "<p>" + CONTENT_TEXT + "</p><p>" + CONTENT_TEXT + "</p>";
-
-        final String htmlArticle =
-            "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<div itemscope itemtype=\"http://schema.org/BlogPosting\">" + article + "</div>";
-
-        assertExtractor(article, htmlArticle);
-    }
-
-    public void testOnlyProcessOGArticleNested() {
-        final String paragraph = "<p>" + CONTENT_TEXT + "</p>";
-        final String article = paragraph + paragraph;
-
-        final String htmlArticle =
-            "<h1>" + CONTENT_TEXT + "</h1>" +
-            "<div itemscope itemtype=\"http://schema.org/Article\">" +
-                paragraph +
-                "<div itemscope itemtype=\"http://schema.org/Article\">" + paragraph + "</div>" +
-            "</div>";
-
-        assertExtractor(article, htmlArticle);
-    }
-
-    public void testOnlyProcessOGNonArticleMovie() {
-        final String article = "<p>" + CONTENT_TEXT + "</p><p>" + CONTENT_TEXT + "</p>";
-
-        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);
-    }
-
     public void testDropCap() {
         String html =
             "<h1>" +
                 CONTENT_TEXT +
             "</h1>" +
             "<p>" +
                 "<strong><span style=\"float: left\">T</span>est</strong>" +
                 CONTENT_TEXT +
             "</p>";
 
         final String expected =
             "<h1>" +
                 CONTENT_TEXT +
             "</h1>" +
             "<p>" +
                 "<strong><span>T</span>est</strong>" +
                 CONTENT_TEXT +
             "</p>";
 
         mBody.setInnerHTML(html);
 
         ContentExtractor extractor = new ContentExtractor(mRoot);
         String extractedContent = extractor.extractContent();
         assertEquals(expected,
                 TestUtil.removeAllDirAttributes(extractedContent));
     }
 }