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.ExtractionContext;
21  import org.apache.any23.extractor.ExtractionException;
22  import org.apache.any23.extractor.ExtractionParameters;
23  import org.apache.any23.extractor.ExtractionResult;
24  import org.apache.any23.extractor.ExtractorDescription;
25  import org.apache.any23.extractor.IssueReport;
26  import org.apache.any23.vocab.XHTML;
27  import org.apache.any23.extractor.Extractor.TagSoupDOMExtractor;
28  import org.eclipse.rdf4j.model.IRI;
29  import org.w3c.dom.Document;
30  import org.w3c.dom.Node;
31  
32  import java.io.IOException;
33  
34  /**
35   * Extractor for the <a href="http://microformats.org/wiki/rel-license">rel-license</a>
36   * microformat.
37   *
38   * @author Gabriele Renzi
39   * @author Richard Cyganiak
40   */
41  public class LicenseExtractor implements TagSoupDOMExtractor {
42  
43      private static final XHTML vXHTML = XHTML.getInstance();
44  
45      @Override
46      public void run(
47              ExtractionParameters extractionParameters,
48              ExtractionContext extractionContext,
49              Document in,
50              ExtractionResult out
51      ) throws IOException, ExtractionException {
52          HTMLDocumentTMLDocument.html#HTMLDocument">HTMLDocument document = new HTMLDocument(in);
53          final IRI documentIRI = extractionContext.getDocumentIRI();
54          for (Node node : DomUtils.findAll(in, "//A[@rel='license']/@href")) {
55              String link = node.getNodeValue();
56              if ("".equals(link)) {
57                  out.notifyIssue(
58                          IssueReport.IssueLevel.WARNING,
59                          String.format(
60                                  "Invalid license link detected within document %s.",
61                                  documentIRI.toString()
62                          ),
63                          0, 0
64                  );
65                  continue;
66              }
67              out.writeTriple(documentIRI, vXHTML.license, document.resolveIRI(link));
68          }
69      }
70  
71      @Override
72      public ExtractorDescription getDescription() {
73          return LicenseExtractorFactory.getDescriptionInstance();
74      }
75      
76  }