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.openrdf.model.URI;
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> the type of the input data to be processed.
30   */
31  public interface Extractor<Input> {
32  
33      /**
34       * This interface specializes an {@link Extractor} able to handle
35       * {@link java.net.URI} as input format. Use it if you need to fetch a document before the extraction
36       */
37      public interface BlindExtractor extends Extractor<URI> {
38      }
39  
40      /**
41       * This interface specializes an {@link Extractor} able to handle
42       * {@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,
48           * if<code>false</code> the extractor will attempt to ignore all parsing errors.
49           *
50           * @param f tolerance flag.
51           */
52          void setStopAtFirstError(boolean f);
53  
54      }
55  
56      /**
57       * This interface specializes an {@link Extractor} able to handle
58       * {@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
65       * not reusable.
66       *
67       * @param extractionParameters the parameters to be applied during the extraction.
68       * @param context The document context.
69       * @param in The extractor input data.
70       * @param out the collector for the extracted data.
71       * @throws IOException On error while reading from the input stream.
72       * @throws ExtractionException On other error, such as parse errors.
73       */
74      void run(ExtractionParameters extractionParameters, ExtractionContext context, Input in, ExtractionResult out)
75      throws IOException, ExtractionException;
76  
77      /**
78       * Returns a {@link ExtractorDescription} of this extractor.
79       *
80       * @return the object representing the extractor description.
81       */
82      ExtractorDescription getDescription();
83  
84  }