lucene-索引word文档

1、通过POI项目来索引。

public class POIWordDocHandler implements DocumentHandler{

public Document getDocument(InputStream is)throws DocumentHandlerException{

StringbodyText=null;

try{//提取文本字段,接收word文档的inputstream对象，允许把原文写入writer类，从wrtier类提取

WordDocument wd=new wordDocument(is);

StringWriterdocTextWriter=new StringWriter();

wd.writeAllText(bew PrintWriter(docTextWriter));

docTextWriter.close();

bodyText=docTextWriter.toString();

}

catch(Exception e){

throw new DocumentHandlerException("cannot extracttext from a word document",e);

}

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

Document doc=new Document();

doc.add(Field.UnStored("body",bodyText));

return doc;

}

returnnull;

}

public static void main() throwsException{

POIWordDocHandler handler=new POIWordDocHandler();

Documentdoc=handler.getDocument(new FileInputStream(newFile(args[0])));

System.out.println(doc);

}

}

2、使用TextMining.org包API,支持从WORD6/95

public class TextMiningWordDocHandler implementsDocumentHandler{

publicDocument getDocument throws DocumentHandlerException(){

String bodyText=null;

try{

bodyText=newWordExtractor().extractText(is);//从InputStream对象中提取文本

}

catch (Exception e){

throw new DocumentHandlerException("cannot extract text from a worddocument",e);

}

 

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

Document doc=new Document();

doc.add(Field.unStored("body",bodyText));

return doc;

}

return null;

}

 

publicstatic void main(String[] args) throws Exception{

TextMiningWordDocHandler handler=newTextMiningWordDocHandler();

Document doc=handler.getDocument(new FileInputStream(newFile(args[0])));

System.out.println(doc);

}

}