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.xpath;
19  
20  import org.apache.any23.extractor.ExtractionResult;
21  import org.eclipse.rdf4j.model.IRI;
22  import org.w3c.dom.Document;
23  
24  /**
25   * Defines an extraction rule for the {@link XPathExtractor}.
26   *
27   * @author Michele Mostarda (mostarda@fbk.eu)
28   */
29  public interface XPathExtractionRule {
30  
31      /**
32       * @return the human readable rule name.
33       */
34      String getName();
35  
36      /**
37       * Checks if the rule can be applied on the given document <i>IRI</i>.
38       *
39       * @param uri
40       *            input document IRI.
41       * 
42       * @return <code>true</code> if applied, <code>false</code> otherwise.
43       */
44      boolean acceptIRI(IRI uri);
45  
46      /**
47       * Processes this extraction rule on the given document.
48       *
49       * @param in
50       *            input document to be processed.
51       * @param out
52       *            output result writer.
53       */
54      void process(Document in, ExtractionResult out);
55  
56  }