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.ExtractionResult;
22  import org.apache.any23.rdf.RDFUtils;
23  import org.eclipse.rdf4j.model.BNode;
24  import org.w3c.dom.Node;
25  
26  import java.util.List;
27  
28  /**
29   * Base class for microformat extractors based on entities.
30   *
31   * @author Gabriele Renzi
32   */
33  public abstract class EntityBasedMicroformatExtractor extends MicroformatExtractor {
34  
35      /**
36       * Returns the base class name for the extractor.
37       *
38       * @return a string containing the base of the extractor.
39       */
40      protected abstract String getBaseClassName();
41  
42      /**
43       * Resets the internal status of the extractor to prepare it to a new extraction section.
44       */
45      protected abstract void resetExtractor();
46  
47      /**
48       * Extracts an entity from a <i>DOM</i> node.
49       *
50       * @param node
51       *            the DOM node.
52       * @param out
53       *            the extraction result collector.
54       * 
55       * @return <code>true</code> if the extraction has produces something, <code>false</code> otherwise.
56       * 
57       * @throws ExtractionException
58       *             if there is an error during extraction
59       */
60      protected abstract boolean extractEntity(Node node, ExtractionResult out) throws ExtractionException;
61  
62      @Override
63      public boolean extract() throws ExtractionException {
64          List<Node> nodes = DomUtils.findAllByClassName(getHTMLDocument().getDocument(), getBaseClassName());
65          boolean foundAny = false;
66          int count = 1;
67          for (Node node : nodes) {
68              resetExtractor();
69              String contextID = Integer.toString(count);
70              ExtractionResult subResult = openSubResult(getExtractionContext().copy(contextID));
71              foundAny |= extractEntity(node, subResult);
72              subResult.close();
73              count++;
74          }
75          return foundAny;
76      }
77  
78      /**
79       * @param node
80       *            a DOM node representing a blank node
81       * 
82       * @return an RDF blank node corresponding to that DOM node, by using a blank node ID like "MD5 of
83       *         http://doc-uri/#xpath/to/node"
84       */
85      protected BNode getBlankNodeFor(Node node) {
86          return RDFUtils.getBNode(getDocumentIRI() + "#" + DomUtils.getXPathForNode(node));
87      }
88  
89  }