This project has retired. For details please refer to its Attic page.
TurtleHTMLExtractorTest xref
View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *  http://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  
18  package org.apache.any23.extractor.html;
19  
20  import org.apache.any23.extractor.ExtractionException;
21  import org.apache.any23.extractor.ExtractorFactory;
22  import org.junit.Test;
23  import org.eclipse.rdf4j.model.Value;
24  import org.slf4j.Logger;
25  import org.slf4j.LoggerFactory;
26  
27  import java.io.IOException;
28  
29  /**
30   * Test case for {@link TurtleHTMLExtractor}.
31   *
32   * @author Michele Mostarda (mostarda@fbk.eu)
33   */
34  public class TurtleHTMLExtractorTest extends AbstractExtractorTestCase {
35  
36      private static final Logger logger = LoggerFactory.getLogger(TurtleHTMLExtractor.class);
37  
38      @Override
39      protected ExtractorFactory<?> getExtractorFactory() {
40          return new TurtleHTMLExtractorFactory();
41      }
42  
43      /**
44       * Tests the extraction of the RDF content from the sample HTML file.
45       * 
46       * @throws IOException
47       *             if there is an error interpreting the input data
48       * @throws ExtractionException
49       *             if there is an exception during extraction
50       * @throws org.eclipse.rdf4j.repository.RepositoryException
51       *             if an error is encountered whilst loading content from a storage connection
52       */
53      @Test
54      public void testExtraction() throws Exception {
55          assertExtract("/html/html-turtle.html");
56          logger.debug(dumpModelToRDFXML());
57          assertStatementsSize(null, (Value) null, 10);
58      }
59  
60  }