poiworddochandler.java

基于lucene的 全文检索程序。可以对office等文件pdf文件进行检索

package org.tatan.framework;
import org.apache.poi.hdf.extractor.WordDocument;

import java.io.InputStream;
import java.io.StringWriter;
import java.io.PrintWriter;

public class POIWordDocHandler  {

  public String getDocument(InputStream is)
    throws DocumentHandlerException {

    String bodyText = null;

    try {
      WordDocument wd = new WordDocument(is);
      StringWriter docTextWriter = new StringWriter();
      wd.writeAllText(new PrintWriter(docTextWriter));
      docTextWriter.close();
      bodyText = docTextWriter.toString();
    }
    catch (Exception e) {
      throw new DocumentHandlerException(
        "Cannot extract text from a Word document", e);
    }

    if ((bodyText != null) && (bodyText.trim().length() > 0)) {
     
      return bodyText;
    }
    return null;
  }

 
}