SpecificPlainTextExtractor


1   /*
2    *  Copyright 2005 Blandware (http://www.blandware.com)
3    *
4    *  Licensed under the Apache License, Version 2.0 (the "License");
5    *  you may not use this file except in compliance with the License.
6    *  You may obtain a copy of the License at
7    *
8    *      http://www.apache.org/licenses/LICENSE-2.0
9    *
10   *  Unless required by applicable law or agreed to in writing, software
11   *  distributed under the License is distributed on an "AS IS" BASIS,
12   *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   *  See the License for the specific language governing permissions and
14   *  limitations under the License.
15   */
16  package com.blandware.atleap.common.parsers;
17  
18  import com.blandware.atleap.common.parsers.exception.PlainTextExtractorException;
19  
20  import java.io.InputStream  ;
21  import java.io.Writer  ;
22  
23  /**
24   * An interface for an extractor which will extract a plain text from the
25   * documents of a specific format.
26   *
27   * @author Roman Puchkovskiy <a HREF="mailto:roman.puchkovskiy@blandware.com">
28   * &lt;roman.puchkovskiy@blandware.com&gt;</a>
29   * @version $Revision: 1.4 $ $Date: 2005/08/14 12:27:54 $
30   */
31  public interface SpecificPlainTextExtractor {
32      /**
33       * Extracts a plain text from a document.
34       *
35       * @param input the input stream that supplies a document for extraction
36       * @param output the writer that will accept the extracted text
37       * @param encoding the encoding of the document in <code>input</code>.
38       * Extractor may ignore the <code>encoding</code> if it doesn't make sence
39       * in the corresponding format. Otherwise, if it is <code>null</code>, then
40       * the extractor will choose the encoding itself. If the
41       * <code>encoding</code> make sence and is not <code>null</code>, then the
42       * extractor should use it. If the extractor finds out the encoding from
43       * document by itself, it uses it and ignores given (or default) encoding.
44       * @throws com.blandware.atleap.common.parsers.exception.PlainTextExtractorException throwed on exception raised during
45       * extracting
46       */
47      public void extract(InputStream   input, Writer   output, String   encoding)
48              throws PlainTextExtractorException;
49  
50      /**
51       * <p>
52       * Returns encoding that was used for extracting. If encoding has no sense
53       * for particular document format or it's unknown for extractor, returns
54       * <code>null</code>.
55       * </p>
56       * <p>
57       * This method should be called after calling <code>extract</code>; before
58       * it this method may return anything. 
59       * </p>
60       *
61       * @return encoding used or <code>null</code>
62       */
63      public String   getUsedEncoding();
64  }
65
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags