This project has retired. For details please refer to its Attic page.
OpenIEExtractorTest 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  package org.apache.any23.openie;
18  
19  import java.io.File;
20  import java.io.FileOutputStream;
21  import java.io.IOException;
22  
23  import org.apache.any23.extractor.ExtractionContext;
24  import org.apache.any23.extractor.ExtractionException;
25  import org.apache.any23.extractor.ExtractionParameters;
26  import org.apache.any23.extractor.ExtractionResult;
27  import org.apache.any23.extractor.ExtractionResultImpl;
28  import org.apache.any23.plugin.extractor.openie.OpenIEExtractor;
29  import org.apache.any23.rdf.RDFUtils;
30  import org.apache.any23.util.StreamUtils;
31  import org.apache.any23.writer.RDFXMLWriter;
32  import org.apache.any23.writer.TripleHandler;
33  import org.apache.any23.writer.TripleHandlerException;
34  import org.eclipse.rdf4j.model.IRI;
35  import org.junit.After;
36  import org.junit.Before;
37  import org.junit.Test;
38  import org.slf4j.Logger;
39  import org.slf4j.LoggerFactory;
40  
41  /**
42   * @author lewismc
43   *
44   */
45  public class OpenIEExtractorTest {
46  
47      private static final Logger logger = LoggerFactory.getLogger(OpenIEExtractorTest.class);
48  
49      private OpenIEExtractor extractor;
50  
51      @Before
52      public void setUp() throws Exception {
53          extractor = new OpenIEExtractor();
54      }
55  
56      @After
57      public void tearDown() throws Exception {
58          extractor = null;
59      }
60  
61      @Test
62      public void testExtractFromHTMLDocument() 
63        throws IOException, ExtractionException, TripleHandlerException {
64          final IRI uri = RDFUtils.iri("http://podaac.jpl.nasa.gov/aquarius");
65          extract(uri, "/org/apache/any23/extractor/openie/example-openie.html");
66      }
67      
68      public void extract(IRI uri, String filePath) 
69        throws IOException, ExtractionException, TripleHandlerException {
70        FileOutputStream fos = new FileOutputStream(File.createTempFile("OpenIEExtractorTest", "tmp"));
71        final TripleHandler tHandler = new RDFXMLWriter(fos);
72        final ExtractionContext extractionContext = new ExtractionContext("rdf-openie", uri);
73        final ExtractionResult result = new ExtractionResultImpl(extractionContext, extractor, tHandler);
74        try {
75          extractor.run(
76                  ExtractionParameters.newDefault(),
77                  extractionContext,
78                  StreamUtils.inputStreamToDocument(this.getClass().getResourceAsStream(filePath)),
79                  result
80          );
81        } finally {
82          logger.debug(fos.toString());
83          tHandler.close();
84          result.close();
85        }
86      }
87  
88  }