MSWordTextExtractor


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.textextraction.impl;
17  
18  import java.io.InputStream  ;
19  import org.apache.poi.hwpf.HWPFDocument;
20  import org.apache.poi.hwpf.usermodel.Range;
21  
22  /**
23   * Text extractor for Microsoft Word files.
24   */
25  public class MSWordTextExtractor implements MimetypeTextExtractor {
26      public String   getText(InputStream   is) throws Exception   {
27          HWPFDocument wordDoc = new HWPFDocument(is);
28          Range range = wordDoc.getRange();
29          return range.text();
30      }
31  }
32

A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame

Popular Tags