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