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.filter;
19  
20  import org.apache.any23.extractor.ExtractionContext;
21  import org.apache.any23.extractor.html.TitleExtractor;
22  import org.apache.any23.extractor.html.TitleExtractorFactory;
23  import org.apache.any23.writer.TripleHandler;
24  import org.apache.any23.writer.TripleHandlerException;
25  import org.eclipse.rdf4j.model.Resource;
26  import org.eclipse.rdf4j.model.IRI;
27  import org.eclipse.rdf4j.model.Value;
28  
29  /**
30   * A {@link TripleHandler} that suppresses output of the {@link TitleExtractor} unless some other triples could be
31   * parsed from the document. This is used when we don't want to have single-triple RDF documents around that contain
32   * only the title triple.
33   *
34   * @author Richard Cyganiak (richard@cyganiak.de)
35   */
36  public class IgnoreTitlesOfEmptyDocuments implements TripleHandler {
37  
38      private final ExtractionContextBlocker blocker;
39  
40      public IgnoreTitlesOfEmptyDocuments(TripleHandler wrapped) {
41          blocker = new ExtractionContextBlocker(wrapped);
42      }
43  
44      public void startDocument(IRI documentIRI) throws TripleHandlerException {
45          blocker.startDocument(documentIRI);
46      }
47  
48      public void openContext(ExtractionContext context) throws TripleHandlerException {
49          blocker.openContext(context);
50          if (isTitleContext(context)) {
51              blocker.blockContext(context);
52          }
53      }
54  
55      public void receiveTriple(Resource s, IRI p, Value o, IRI g, ExtractionContext context)
56              throws TripleHandlerException {
57          if (!isTitleContext(context)) {
58              blocker.unblockDocument();
59          }
60          blocker.receiveTriple(s, p, o, g, context);
61      }
62  
63      public void receiveNamespace(String prefix, String uri, ExtractionContext context) throws TripleHandlerException {
64          blocker.receiveNamespace(prefix, uri, context);
65      }
66  
67      public void closeContext(ExtractionContext context) {
68          blocker.closeContext(context);
69      }
70  
71      public void close() throws TripleHandlerException {
72          blocker.close();
73      }
74  
75      private boolean isTitleContext(ExtractionContext context) {
76          return context.getExtractorName().equals(TitleExtractorFactory.NAME);
77      }
78  
79      public void endDocument(IRI documentIRI) throws TripleHandlerException {
80          blocker.endDocument(documentIRI);
81      }
82  
83      public void setContentLength(long contentLength) {
84          // Ignore.
85      }
86  }