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.vocab.XHTML;
26  import org.apache.any23.extractor.Extractor.TagSoupDOMExtractor;
27  import org.eclipse.rdf4j.model.IRI;
28  import org.eclipse.rdf4j.model.ValueFactory;
29  import org.eclipse.rdf4j.model.impl.SimpleValueFactory;
30  import org.w3c.dom.Document;
31  import org.w3c.dom.Node;
32  
33  import java.io.IOException;
34  import java.util.List;
35  
36  /**
37   * This {@link org.apache.any23.extractor.Extractor.TagSoupDOMExtractor} implementation
38   * retrieves the <code>LINK</code>s declared within the <code>HTML/HEAD</code> page header.
39   */
40  public class HeadLinkExtractor implements TagSoupDOMExtractor {
41  
42      public void run(
43              ExtractionParameters extractionParameters,
44              ExtractionContext extractionContext,
45              Document in,
46              ExtractionResult out
47      ) throws IOException, ExtractionException {
48          HTMLDocumentml/HTMLDocument.html#HTMLDocument">HTMLDocument html = new HTMLDocument(in);
49          ValueFactory vf = SimpleValueFactory.getInstance();
50  
51          final List<Node> headLinkNodes = DomUtils.findAll(
52                  in,
53                  "/HTML/HEAD/LINK[(" +
54                          "@type='application/rdf+xml' or " +
55                          "@type='text/rdf' or " +
56                          "@type='application/x-turtle' or " +
57                          "@type='application/turtle' or " +
58                          "@type='text/turtle' or " +
59                          "@type='text/rdf+n3'" +
60                          ") and @href and @rel]"
61          );
62          for (Node node : headLinkNodes) {
63              final IRI href = html.resolveIRI(DomUtils.find(node, "@href"));
64              final String rel = DomUtils.find(node, "@rel");
65              out.writeTriple(
66                      extractionContext.getDocumentIRI(),
67                      vf.createIRI(XHTML.NS + rel),
68                      href
69              );
70              final String title = DomUtils.find(node, "@title");
71              if (title != null && !"".equals(title)) {
72                  out.writeTriple(
73                          href,
74                          getDescription().getPrefixes().expand("dcterms:title"),
75                          vf.createLiteral(title)
76                  );
77              }
78              final String type = DomUtils.find(node, "@type");
79              if (type != null && !"".equals(type)) {
80                  out.writeTriple(
81                          href,
82                          getDescription().getPrefixes().expand("dcterms:format"),
83                          vf.createLiteral(type)
84                  );
85              }
86          }
87      }
88  
89      @Override
90      public ExtractorDescription getDescription() {
91          return HeadLinkExtractorFactory.getDescriptionInstance();
92      }
93  
94  }