/*
* $Header: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/MSWordExtractor.java,v 1.1.2.1 2004/09/29 15:01:26 unico Exp $
* $Revision: 1.1.2.1 $
* $Date: 2004/09/29 15:01:26 $
*
* ====================================================================
*
* Copyright 2004 The Apache Software Foundation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
*/
package org.apache.slide.extractor;
/**
* Author: Ryan Rhodes
* Date: Jun 26, 2004
* Time: 12:34:29 AM
*/
import java.io.*;
import org.textmining.text.extraction.WordExtractor;
public class MSWordExtractor extends AbstractContentExtractor {
public MSWordExtractor(String uri, String contentType, String namespace) {
super(uri, contentType, namespace);
}
public Reader extract(InputStream content) throws ExtractorException {
try {
WordExtractor extractor =
new WordExtractor();
String text = extractor.extractText(content);
StringReader reader = new StringReader(text);
return reader;
}
catch(Exception e) {
throw new ExtractorException(e.getMessage());
}
}
public static void main(String[] args) throws Exception
{
FileInputStream in = new FileInputStream(args[0]);
MSWordExtractor ex = new MSWordExtractor(null, null, null);
Reader reader = ex.extract(in);
int c;
do
{
c = reader.read();
System.out.print((char)c);
}
while( c != -1 );
}
}