DocumentSummarizerImpl


1   /*
2    * Copyright 2004 Outerthought bvba and Schaubroeck nv
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 org.outerj.daisy.summary;
17  
18  import org.outerj.daisy.repository.Document;
19  import org.outerj.daisy.repository.Part;
20  import org.outerj.daisy.repository.schema.RepositorySchema;
21  import org.apache.avalon.framework.logger.AbstractLogEnabled;
22  
23  import java.io.InputStream  ;
24  import java.io.BufferedInputStream  ;
25  
26  
27  /**
28   * @avalon.component version="1.0" name="summarizer" lifestyle="singleton"
29   * @avalon.service type="org.outerj.daisy.summary.DocumentSummarizer"
30   */
31  public class DocumentSummarizerImpl extends AbstractLogEnabled implements DocumentSummarizer {
32      private static final int SUMMARY_LENGTH = 300;
33  
34      public String   getSummary(Document document, long versionId, RepositorySchema repositorySchema) throws Exception   {
35          Part[] parts = null;
36  
37          if (versionId == -1) {
38              parts = document.getPartsInOrder().getArray();
39          } else {
40              parts = document.getVersion(versionId).getPartsInOrder().getArray();
41          }
42  
43          for (int i = 0; i < parts.length; i++) {
44              Part part = parts[i];
45              if (part.getMimeType().equals("text/xml")) {
46                  boolean daisyHtml = repositorySchema.getPartTypeById(part.getTypeId(), false).isDaisyHtml();
47                  if (daisyHtml) {
48                      String   summary;
49                      InputStream   is = new BufferedInputStream  (part.getDataStream());
50                      try {
51                          summary = HtmlSummarizer.extractSummary(is, SUMMARY_LENGTH);
52                      } finally {
53                          is.close();
54                      }
55                      return summary;
56                  }
57              }
58          }
59  
60          return null;
61      }
62  }
63
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags