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;
19  
20  import org.eclipse.rdf4j.model.IRI;
21  import org.w3c.dom.Document;
22  
23  import java.io.IOException;
24  import java.io.InputStream;
25  
26  /**
27   * It defines the signature of a generic Extractor.
28   *
29   * @param <Input>
30   *            the type of the input data to be processed.
31   */
32  public interface Extractor<Input> {
33  
34      /**
35       * This interface specializes an {@link Extractor} able to handle {@link java.net.URI} as input format. Use it if
36       * you need to fetch a document before the extraction
37       */
38      public interface BlindExtractor extends Extractor<IRI> {
39      }
40  
41      /**
42       * This interface specializes an {@link Extractor} able to handle {@link java.io.InputStream} as input format.
43       */
44      public interface ContentExtractor extends Extractor<InputStream> {
45  
46          /**
47           * If <code>true</code>, the extractor will stop at first parsing error, if<code>false</code> the extractor will
48           * attempt to ignore all parsing errors.
49           *
50           * @param f
51           *            tolerance flag.
52           */
53          void setStopAtFirstError(boolean f);
54  
55      }
56  
57      /**
58       * This interface specializes an {@link Extractor} able to handle {@link org.w3c.dom.Document} as input format.
59       */
60      public interface TagSoupDOMExtractor extends Extractor<Document> {
61      }
62  
63      /**
64       * Executes the extractor. Will be invoked only once, extractors are not reusable.
65       *
66       * @param extractionParameters
67       *            the parameters to be applied during the extraction.
68       * @param context
69       *            The document context.
70       * @param in
71       *            The extractor input data.
72       * @param out
73       *            the collector for the extracted data.
74       * 
75       * @throws IOException
76       *             On error while reading from the input stream.
77       * @throws ExtractionException
78       *             On other error, such as parse errors.
79       */
80      void run(ExtractionParameters extractionParameters, ExtractionContext context, Input in, ExtractionResult out)
81              throws IOException, ExtractionException;
82  
83      /**
84       * Returns a {@link ExtractorDescription} of this extractor.
85       *
86       * @return the object representing the extractor description.
87       */
88      ExtractorDescription getDescription();
89  
90  }